EP2879386B1 - Three-dimensional object detection device, and three-dimensional object detection method - Google Patents
Three-dimensional object detection device, and three-dimensional object detection method Download PDFInfo
- Publication number
- EP2879386B1 EP2879386B1 EP13823494.3A EP13823494A EP2879386B1 EP 2879386 B1 EP2879386 B1 EP 2879386B1 EP 13823494 A EP13823494 A EP 13823494A EP 2879386 B1 EP2879386 B1 EP 2879386B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- edge
- dimensional object
- area
- intensity
- edge intensity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims description 406
- 238000000605 extraction Methods 0.000 claims description 150
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 66
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 66
- 238000006243 chemical reaction Methods 0.000 claims description 26
- 230000007423 decrease Effects 0.000 claims description 20
- 230000035945 sensitivity Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 238000000034 method Methods 0.000 description 62
- 230000008569 process Effects 0.000 description 43
- 230000008859 change Effects 0.000 description 29
- 230000000694 effects Effects 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 9
- 230000004907 flux Effects 0.000 description 7
- 239000013256 coordination polymer Substances 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 239000010409 thin film Substances 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
- H04N23/81—Camera processing pipelines; Components thereof for suppressing or minimising disturbance in the image signal generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/60—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective
- B60R2300/607—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective from a bird's eye viewpoint
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/802—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for monitoring and displaying vehicle exterior blind spot views
- B60R2300/8026—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for monitoring and displaying vehicle exterior blind spot views in addition to a rear-view mirror system
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B2217/00—Details of cameras or camera bodies; Accessories therefor
- G03B2217/005—Blur detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N2101/00—Still video cameras
Definitions
- the present invention relates to a three-dimensional object detection device and a three-dimensional object detection method.
- Patent Document 1 a three-dimensional object near a host vehicle is detected based on a captured image captured by a camera.
- Patent Document 1 Japanese Laid-Open Patent Application No. 2006-311216 US 2006/0115121 A1 refers to an abnormality detecting apparatus for an imaging apparatus that detects the presence of abnormalities in an imaging apparatus mounted on a vehicle.
- the abnormality detecting apparatus has the object to detect the presence of abnormal conditions, for example grime in an optical system, in an imaging apparatus.
- the abnormality detecting apparatus comprising an image capturing means, like infrared cameras which are mounted in front of a vehicle, and a region setting device that sets a region in the image made by the image capturing means such that a luminance variance value calculating device that can- calculate a luminance variance value for determining whether an abnormality has occurred in the image capturing means.
- the problem to be solved by the present invention is to provide a three-dimensional object detection device that is capable of appropriately detecting a three-dimensional object, even when the lens is clouded.
- the problem is solved according to the invention by a three-dimensional object detection device comprising the features of claim 1.
- Advantageous embodiments can be derived from the subclaims.
- a three-dimensional object detection device which detects a three-dimensional object based on a captured image, extracts the edges of a subject in a first edge extraction area, including a horizon reference area that references the horizon, and calculates the intensity of the edges based on the distribution of the edges extracted from the first edge extraction area as a first edge intensity; the three-dimensional object detection device then extracts the edges of a subject in a second edge extraction area, including a road edge reference area that references the road edge, and calculates the intensity of the edges based on the distribution of the edges extracted from the second edge extraction area as a second edge intensity.
- the three-dimensional object detection device then controls the detection of a three-dimensional object based on the first edge intensity in the first edge extraction area during the daytime while controlling the detection of a three-dimensional object based on the second edge intensity in the second edge extraction area when an assessment has been made that nighttime has fallen, thereby solving the problem.
- the present invention by extracting the edges from a first edge extraction area from which the extraction of a predetermined quantity of edges are expected during the daytime or by extracting the edges from a second edge extraction area from which the extraction of a predetermined quantity of edges are expected during the nighttime, and then calculating the intensity of the edges, appropriately determining whether or not the lens is clouded according to the surrounding light environment based on the intensity of the edges is possible. Then, by controlling the detection of a three-dimensional object based on the intensity of the edges, appropriately detecting a three-dimensional object even when the lens is clouded is possible.
- the invention is set out in the appended set of claims.
- FIG. 1 is a schematic overview of a vehicle equipped with a three-dimensional object detection device 1 according to the present embodiment.
- An objective of the three-dimensional object detection device 1 according to the present embodiment is to detect another vehicle (which may hereinafter be referred to as adjacent vehicle V2) present in an adjacent lane where contact is possible should a host vehicle V1 change lanes.
- the three-dimensional object detection device 1 according to the present embodiment is provided with a camera 10, a vehicle speed sensor 20, and a computer 30, as illustrated in FIG. 1 .
- the camera 10 is attached to the host vehicle V1 so that the optical axis is an angle ⁇ downward from the horizontal axis in a location at a height h at the rear of the host vehicle V1, as illustrated in FIG. 1 . From this position, the camera 10 captures a predetermined area of the surrounding environment of the host vehicle V1.
- the vehicle speed sensor 20 detects the driving speed of the host vehicle V1 and calculates the vehicle speed from a wheel speed detected by, for example, a wheel speed sensor for detecting the rotational speed of a wheel.
- the computer 30 detects when an adjacent vehicle is present in an adjacent lane rearward of the host vehicle.
- FIG. 2 is a plan view illustrating the driving state of the host vehicle V1 in FIG. 1 .
- the camera 10 captures the rear side of the vehicle at a predetermined view angle a.
- the view angle a of the camera 10 is set to a view angle that allows the left and right lanes (the adjacent lanes) to be captured in addition to the lane in which the host vehicle V1 1 is driving.
- FIG. 3 is a block view illustrating the details of the computer 30 according to the first embodiment.
- the camera 10 and the vehicle speed sensor 20 are also illustrated in FIG. 3 in order to distinctly indicate the connection relationships.
- the computer 30 is provided with a viewpoint conversion unit 31, an alignment unit 32, a three-dimensional object detection unit 33, a day/night assessment unit 34, an edge extraction area setting unit 35, an edge intensity calculation unit 36, and a threshold value changing unit 37.
- a viewpoint conversion unit 31 an alignment unit 32, a three-dimensional object detection unit 33, a day/night assessment unit 34, an edge extraction area setting unit 35, an edge intensity calculation unit 36, and a threshold value changing unit 37.
- Captured image data of the predetermined area obtained by the camera 10 is input into the viewpoint conversion unit 31, and the captured image data thus input is converted into bird's-eye view image data, which is a bird's-eye view state.
- a bird's-eye view state is a state of viewing from a viewpoint of an imaginary camera that is looking down from above, in particular, vertically downward. Viewpoint conversion can be carried out in the manner described in, for example, Japanese Laid-Open Patent Application No. 2008-219063 .
- the reason that captured image data is converted into bird's-eye view image data is based on the principle that perpendicular edges unique to a three-dimensional object are converted into a straight-line group that passes through a specific fixed point by viewpoint conversion into bird's-eye view image data; utilizing this principle allows a planar object to be differentiated from a three-dimensional object.
- FIG. 4 is a view showing the general overview of the processing of the alignment unit 32;
- FIG. 4(a) is a plan view illustrating the moving state of the host vehicle V1
- FIG. 4(b) is an image illustrating a general overview of the alignment.
- the host vehicle V1 at the current moment is positioned at P 1
- the host vehicle V1 at a single moment prior is positioned at P 1 '.
- An assumption is made that an adjacent vehicle V2 is positioned at the rear of the host vehicle V1 and is driving parallel to the host vehicle V1; additionally, an assumption is made that the adjacent vehicle V2 at the current moment is positioned at P 2 and that the adjacent vehicle V2 at a single moment prior is positioned at P 2 '.
- an assumption is made that the host vehicle V1 has moved a distance d in a single moment.
- the phrase "at a single moment prior" may be a moment in the past at a time set in advance (for example, a single control cycle) from the current moment, or this may be a moment in the past at an arbitrary time.
- a bird's-eye view image PB t at the current moment is illustrated in FIG. 4(b) .
- the white lines drawn on the road surface are rectangular in this bird's-eye view image PB t and are relatively accurate in a planar view, but the adjacent vehicle V2 (position P 2 ) is collapsed.
- the white lines drawn on the road surface are rectangular and are relatively accurate in a planar view, but the adjacent vehicle V2 (position P 2 ') is collapsed.
- the perpendicular edges of a three-dimensional object appear as a straight-line group along a collapsing direction due to the operation for converting the viewpoint into bird's-eye view image data; however, because a planar image on the road surface does not include perpendicular edges, such collapsing does not occur even when the viewpoint has been converted.
- the alignment unit 32 aligns the bird's-eye view images PB t and PB t-1 , such as those described above, in terms of data. When this is carried out, the alignment unit 32 offsets the bird's-eye view image PB t-1 at a single moment prior and matches the position with the bird's-eye view image PB t at the current moment.
- the left-side image and the center image in FIG. 4(b) illustrate the offset state by a travel distance d'.
- the offset amount d' is the amount of movement in the bird's-eye view image data that corresponds to the actual travel distance d of the host vehicle V1 illustrated in FIG. 4(a) and is determined based on a signal from the vehicle speed sensor 20 and the time from a single moment prior to the current moment.
- the alignment unit 32 in the present embodiment aligns in a bird's-eye view the positions of the bird's-eye view images obtained at different times and obtains the aligned bird's-eye view images; however, the "alignment" process may precisely be carried out corresponding to the type of objects to be detected or to the required precision for detection.
- the operation may be a strict alignment process in which alignment is conducted based on the same time and the same position or based on a loose alignment in which the coordinates of each bird's-eye view image are grasped.
- the alignment unit 32 obtains the difference between the bird's-eye view images PB t and PB t-1 and generates differential image PD 1 data.
- the alignment unit 32 takes the absolute value of the difference in the pixel values of the bird's-eye view images PB t and PBt-1 in order correspond to the variation in the illumination environment; when the absolute value is equal to or greater than a predetermined threshold value th, the pixel values of the differential image PD t are set to "1;" and when the absolute value is less than a predetermined threshold value th, the pixel values of the differential image PD t are set to "0," which allows differential image PD t data, such as that illustrated on the right side of FIG.
- the value of the difference threshold value th is changed by the threshold value changing unit 37 mentioned below; when the difference threshold value th is changed by the threshold value changing unit 37, the pixel values of the differential image PD t are detected using the difference threshold value th that is changed by the threshold value changing unit 37.
- the three-dimensional object detection unit 33 then detects a differential waveform based on the differential image PD t data illustrated in FIG. 4(b) . In this case, the three-dimensional object detection unit 33 calculates the travel distance of the three-dimensional object in real space. The three-dimensional object detection unit 33 first generates a first differential waveform when the three-dimensional object is detected and the travel distance is to be calculated.
- the three-dimensional object detection unit 33 sets a detection area (a detection frame) in the differential image PD t .
- An objective of the three-dimensional object detection device 1 of the present example is to calculate the travel distance for the adjacent vehicle with which there is a possibility of contact should the host vehicle V1 change lanes. Accordingly, in the present example, rectangular detection areas (the detection frames) A1, A2 are set behind the host vehicle V1, as illustrated in FIG. 2 . Such detection areas A1, A2 may be set from a relative position to the host vehicle V1, or they may be set based on the position of the white lines. When set based on the position of the white lines, the three-dimensional object detection device 1 may use, for example, what is known as white line recognition techniques.
- the three-dimensional object detection unit 33 recognizes as ground lines L1, L2 the borders of the detection areas A1, A2 thus set on the host vehicle V1 side (the side along the traveingl direction), as illustrated in FIG. 2 .
- a ground line refers to a line in which a three-dimensional object is in contact with the ground; however, in the present embodiment, a ground line is not a line in contact with the ground but is rather set in the manner described above. Even in such a case, the difference between the ground line according to the present embodiment and a normal ground line that is determined from the position of the adjacent vehicle V2 is not exceedingly great as determined by experience, and there is no problem in actuality.
- FIG. 5 is a schematic view illustrating the manner in which a differential waveform is generated by the three-dimensional object detection unit 33.
- the three-dimensional object detection unit 33 generates a differential waveform DW t from the portion that corresponds to the detection areas A1, A2 in the differential image PD t (the drawing on the right in FIG. 4(b) ) calculated by the alignment unit 32.
- the three-dimensional object detection unit 33 generates the differential waveform DW t along the collapsing direction of the three-dimensional object by viewpoint conversion.
- the detection area A1 will be described for the sake of convenience, but the differential waveform DWt is also generated for the detection area A2 using the same procedure.
- the three-dimensional object detection unit 33 defines a line La in the direction in which the three-dimensional object collapses in the differential image PD t data.
- the three-dimensional object detection unit 33 then counts the number of difference pixels DP indicating a predetermined difference on the line La.
- the difference pixels DP indicating a predetermined difference have pixel values in the differential image PD t that are represented by "0" and "1,” with the pixels indicated by a "1" being counted as difference pixels DP.
- the three-dimensional object detection unit 33 counts the number of difference pixels DP and then determines the crossing point CP of the line La and the ground line L1.
- the three-dimensional object detection unit 33 then correlates the crossing point CP and the count number; decides the horizontal-axis position, in particular, the position on the axis in the vertical direction in the drawing on the right in FIG. 5 , based on the position of the crossing point CP; decides the vertical-axis position, in particular, the position on the axis in the lateral direction in the drawing on the right in FIG. 5 , from the count number; and plots the positions as the count number at the crossing point CP.
- the three-dimensional object detection unit 33 defines the lines Lb, Lc, ... in the direction in which the three-dimensional object collapses, counts the number of difference pixels DP, decides the horizontal-axis position based on the position of each crossing point CP, decides the vertical-axis position from the count number (the number of difference pixels DP), and plots the positions.
- the three-dimensional object detection unit 33 repeats the above in sequence to form a frequency distribution, thereby generating a differential waveform DW t as illustrated in the drawing on the right in FIG. 5 .
- the difference pixels PD in the differential image PD t data are pixels that have changed in the image at different moments; in other words, they are locations that can be construed to be where a three-dimensional object was present. Accordingly, in locations where a three-dimensional object was present, the number of pixels is counted along the direction in which the three-dimensional object collapses to form a frequency distribution, thereby generating a differential waveform DW t . In particular, the number of pixels is counted along the direction in which the three-dimensional object collapses, and a differential waveform DW t is therefore generated from information about the height direction in relation to the three-dimensional object.
- the lines La and Lb in the direction in which the three-dimensional object collapses have different distances that overlap the detection area A1, as illustrated in the drawing on the left in FIG. 5 . Accordingly, the number of difference pixels DP is greater on the line La than on the line Lb when an assumption is made that the detection area A1 is filled with the difference pixels DP. For this reason, the three-dimensional object detection unit 33 performs normalization based on the distance that the lines La, Lb in the direction in which the three-dimensional object collapses and the detection area A1 overlap when the vertical-axis position is determined from the count number of the difference pixels DP. In a specific example, there are six difference pixels DP on the line La, and there are five difference pixels DP on the line Lb in the drawing on the left in FIG.
- the three-dimensional object detection unit 33 divides the count number by the overlapping distance or performs normalization in another manner.
- the values of the differential waveform DW t that correspond to the lines La, Lb in the direction in which the three-dimensional object collapses are thereby made to be substantially the same, as illustrated in the differential waveform DW t .
- FIG. 6 is a view showing the method for detecting a three-dimensional object by the three-dimensional object detection unit 33 and shows an example of the threshold value ⁇ for detecting a differential waveform DW t and a three-dimensional object.
- the three-dimensional object detection unit 33 determines whether or not a three-dimensional object is present in the detection areas A1, A2 by determining whether the peak of the generated differential waveform DW t is at a predetermined threshold value ⁇ corresponding to the peak position of the differential waveform DW t or greater, as illustrated in FIG. 6 .
- the three-dimensional object detection unit 33 determines that a three-dimensional object is not present in the detection areas A1, A2 when the peak of the differential waveform DW t is less than the predetermined threshold value ⁇ ;, when the peak of the differential waveform DW t is at a predetermined threshold value ⁇ or greater, the determination is that a three-dimensional object is present in the detection areas A1, A2.
- the three-dimensional object detection unit 33 calculates the travelling speed of the three-dimensional object by comparing the differential waveform DW t at the current moment with the differential waveform DWt-1 at a single moment prior. In other words, the three-dimensional object detection unit 33 calculates the travelling speed of the three-dimensional object from the change in time of the differential waveforms DW t , DWt-1.
- the three-dimensional object detection unit 33 divides the differential waveform DW t into a plurality of small areas DWt1 to DW tn (where n is an arbitrary integer of 2 or greater), as illustrated in FIG. 7.
- FIG. 7 is a view illustrating the small areas DWt1 to DW tn divided by the three-dimensional object detection unit 33.
- the small areas DWt1 to DW tn are divided so as to be mutually overlapping, as illustrated in, for example, FIG. 7 .
- the small area DWt1 and the small area DWt2 overlap each other, and the small area DWt2 and the small area DWt3 overlap each other.
- the three-dimensional object detection unit 33 determines the offset amount (the amount of movement in the horizontal-axis direction (the vertical direction in FIG. 7 ) of the differential waveform) for each of the small areas DWt1 to DW tn .
- the offset amount is determined from the difference (the distance in the horizontal-axis direction) between the differential waveform DWt-1 at a single moment prior and the differential waveform DW t at the current moment.
- the three-dimensional object detection unit 33 moves the differential waveform DWt-1 at a single moment prior in the horizontal-axis direction for each of the small areas DWt1 to DW tn , thereby assessing the position (the position in the horizontal-axis direction) in which the error from the differential waveform DW t at the current moment is at a minimum; then, the three-dimensional object detection unit determines as the offset amount the movement amount in the horizontal-axis direction at the position in which the error from the original position of the differential waveform DWt-1 is at a minimum. The three-dimensional object detection unit 33 then counts the offset amount determined for each of the small areas DWt1 to DW tn and forms a histogram.
- FIG. 8 is a view illustrating an example of the histogram obtained by the three-dimensional object detection unit 33.
- the offset amount which is the movement amount in which the error between the small areas DWt1 to DW tn and the differential waveform DWt-1 at a single moment prior is at a minimum.
- the three-dimensional object detection unit 33 forms the offset amounts including the variability into a histogram and calculates the travel distance from the histogram.
- the three-dimensional object detection unit 33 calculates the travel distance of the three-dimensional object (the adjacent vehicle V2) from the maximum value in the histogram.
- the offset amount is the movement amount in which the error between the small areas DWt1 to DW tn and the differential waveform DWt-1 at a single moment prior is at a minimum.
- the three-dimensional object detection unit 33 forms the offset amounts including the variability into a histogram and calculates the travel distance from the histogram.
- the three-dimensional object detection unit 33 calculates the travel distance of the three-dimensional object (the
- the three-dimensional object detection unit 33 calculates the offset amount indicating the maximum value of the histogram as the travel distance ⁇ *. In this manner, in the present embodiment, a more highly accurate travel distance can be calculated from the maximum value, even when the offset amount varies.
- the travel distance ⁇ * is the relative travel distance of the three-dimensional object (the adjacent vehicle V2) in relation to the host vehicle. Accordingly, the three-dimensional object detection unit 33 calculates the absolute travel distance based on the travel distance ⁇ * thus obtained and the vehicle speed sensor 20 when the absolute travel distance is to be calculated.
- the travel distance of the three-dimensional object (the adjacent vehicle V2) is calculated from the offset amount of the differential waveform DW t when the error in the differential waveform DW t generated at different moments is at a minimum; this allows the travel distance to be calculated from the offset amount, which is information about one dimension in a waveform, and allows the computation costs to be kept low when the travel distance is calculated.
- the travel distance of the three-dimensional object is calculated from the change in time of the differential waveform DW t , which includes the height direction information.
- the detection location prior to a change in time and the detection location after a change in time are specified with the height direction information included and accordingly readily end up being the same location; the travel distance is calculated from the change in time at the same location; and the precision for calculating the travel distance can be improved.
- the three-dimensional object detection unit 33 may impart a weighting to the plurality of small areas DWt1 to DW m and may count the offset amounts determined for each of the small areas DWt1 to DWtn in accordance with the weighting to form a histogram.
- FIG. 9 is a view illustrating the weighting used by the three-dimensional object detection unit 33.
- a small area DW m (where m is an integer 1 or greater, and n is - 1 or less) is flat.
- the three-dimensional object detection unit 33 reduces the weighting of this type of small area DW m . This is because the flat small area DW m lacks a characteristic, and there is a high possibility that an error will be magnified when the offset amount is calculated.
- a small area DW m+k (where k is an integer n - m or less) has abundant undulation.
- the three-dimensional object detection unit 33 increases the weighting of this type of small area DW m . This is because the small area DW m+k abundant in undulation is characteristic and there is a high possibility that the offset amount will be accurately calculated. Weighting the small areas in this manner facilitates a more precise calculation of the travel distance.
- the differential waveform DW t is divided into a plurality of small areas DWt1 to DW tn in the present embodiment in order to enhance the precision for calculating the travel distance, but a division into the small areas DWt1 to DW tm , is not required when the precision for calculating travel distance is not necessary.
- the three-dimensional object detection unit 33 calculates the travel distance from the offset amount of the differential waveform DW t when the error between the differential waveform DW t and the differential waveform DWt-1 is at a minimum.
- the method for determining the offset amount between the differential waveform DWt-1 at a single moment prior and the differential waveform DW t at the current moment is not limited to the details described above.
- the three-dimensional object detection unit 33 in the present embodiment determines the travelling speed of the host vehicle V1 (the camera 10) and determines the offset amount for a stationary object from the determined travelling speed. After the offset amount of the stationary object has been determined, the three-dimensional object detection unit 33 ignores the offset amount that corresponds to the stationary object within the maximum value of the histogram and calculates the travel distance of the three-dimensional object.
- FIG. 10 is a view illustrating another example of the histogram obtained by the three-dimensional object detection unit 33.
- a stationary object other than the three-dimensional object is present within the view angle of the camera 10
- two maximum values ⁇ 1, ⁇ 2 appear in the resulting histogram.
- one of the two maximum values ⁇ 1, ⁇ 2 is the offset amount of the stationary object. Consequently, the three-dimensional object detection unit 33 determines the offset amount for the stationary object from the travelling speed, ignores the maximum value that corresponds to the offset amount, and calculates the travel distance of the three-dimensional object using the remaining maximum value. As a result, preventing a situation in which a stationary object reduces the precision for calculating the travel distance of the three-dimensional object is possible.
- the three-dimensional object detection unit 33 stops calculating the travel distance. In the present embodiment, preventing a situation in which an erroneous travel distance is calculated, such as when there is a plurality of maximum values, is thereby possible.
- detecting an adjacent vehicle V2 by detecting a three-dimensional object that is present in the detection areas A1, A2 and determining whether or not the detected three-dimensional object is an adjacent vehicle V2 is possible.
- the present embodiment is provided with a function to assess whether or not the lens is clouded and change the difference threshold th mentioned above according to the turbidity of the lens in order to appropriately detect a three-dimensional object even when the lens of the camera 10 is clouded (when white thin film has caused by a water stain or the like to form on the lens surface).
- the computer 30 of the present embodiment is provided with a day/night assessment unit 34, an edge extraction area setting unit 35, an edge intensity calculation unit 36, and a threshold value changing unit 37. Each of these configurations is described below.
- the day/night assessment unit 34 assesses whether is the present is daytime or nighttime based on a captured image captured by the camera 10.
- the method for assessing day/night by the day/night assessment unit 34 is not particularly limited; for example, the day/night assessment unit 34 can calculate the average luminance of the entire captured image and determine that the present is daytime when the calculated average luminance is a predetermined value or greater; when the calculated average luminance is less than the predetermined value, the determination is that the present is nighttime.
- the day/night assessment unit 34 may assess whether the present is day/night based on the time or based on the detection results of a sensor, such as a luminometer.
- the edge extraction area setting unit 35 sets an area in the captured image from which a predetermined quantity of edges can be expected to be extracted as the edge extraction area.
- the edge extraction area setting unit 35 sets a different area as the edge extraction area when an assessment has been made that the present is nighttime by the day/night assessment unit 34, as compared to when an assessment has been made that the present is daytime.
- the method to set the edge extraction area will be described below referring to the edge extraction area that is set during daytime as the daytime edge extraction area and referring to the edge extraction area set during nighttime as the nighttime edge extraction area.
- the edge extraction area setting unit 35 sets a pair of left and right road edge reference areas (the left-side road edge reference area and the right-side road edge reference area) as the nighttime edge extraction areas when an assessment has been made that the present is nighttime by the day/night assessment unit 34, as illustrated in FIG. 11 .
- This pair of left and right road edge reference areas are areas that respectively include the road edge positioned on the left side and the road edge positioned on the right side of the driving lane of the host vehicle V1; these areas are the areas from which the extraction of a predetermined quantity of edges is expected in the image area corresponding to these road edges.
- the edge extraction area setting unit 35 stores in a memory (not diagrammed) of the computer 30 a plurality of reference points for setting the pair of left and right road edge reference areas using a world coordinate system having the camera 10 as the origin.
- the edge extraction area setting unit 35 then acquires the plurality of reference points for setting the road edge reference areas from the memory of the computer 30 and converts the acquired reference points from the world coordinate system into a camera coordinate system.
- FIG. 12(A) is a view illustrating the reference points of the road edge reference areas that have been converted into a camera coordinate system.
- the edge extraction area setting unit 35 sets the areas that are obtained by connecting the reference points that have been converted into the camera coordinate system with a straight line L 1 and then by expanding from the straight line L 1 to the left and the right directions by a predetermined distance d 1 , as the left-side road edge reference area and the right-side road edge reference area, respectively, as illustrated in FIG. 12(B).
- FIG. 12(B) is an enlarged view of the B portion in FIG. 12(A) .
- the edge extraction area setting unit 35 sets, in addition to the pair of left and right road edge reference areas that reference the road edges, a horizon reference area that references the horizon near the vanishing point, as the daytime edge extraction area, as illustrated in FIG. 13 .
- the horizon reference area is an area that includes the horizon, as well as an area from which the extraction of a predetermined quantity of edges is expected in the image area corresponding to the horizon.
- the pair of left and right road edge reference areas in the daytime edge extraction area can be set in the same way as the pair of left and right road edge reference areas in the nighttime edge extraction area; therefore, the description thereof has been omitted.
- the edge extraction area setting unit 35 stores in a memory (not diagrammed) of the computer 30 a plurality of reference points for setting the horizon reference area using a world coordinate system having the camera 10 as the origin in the same way as with the pair of left and right road edge reference areas.
- the edge extraction area setting unit 35 then acquires the plurality of reference points for setting the horizon reference area from the memory of the computer 30 and converts the acquired reference points from the world coordinate system into the camera coordinate system.
- FIG. 14(A) is a view illustrating the reference points of the horizon reference area that have been converted into a camera coordinate system.
- the edge extraction area setting unit 35 first converts the reference points corresponding to the right side portion into the camera coordinate system, as illustrated in FIG. 14(A) .
- the edge extraction area setting unit 35 then mirrors the reference points corresponding to the right side portion about a straight line L2 that passes the vanishing point and sets the reference points corresponding to the left side portion.
- the edge extraction area setting unit 35 sets the area obtained by connecting adjacent reference points with the straight line L 2 and then by expanding outward from the straight line L 2 (that is, in the right direction in the portion on the right side of the straight line L 2 and in the left direction in the portion on the left side of the straight line L 2 ) by a predetermined distance d 2 as the horizon reference area, as illustrated in FIG. 14(B).
- FIG. 14(B) is an enlarged view of the B portion in FIG. 14(A) .
- the edge extraction area setting unit 35 sets a different edge extraction area when an assessment has been made that the present is nighttime, as compared to when an assessment has been made that the present is daytime.
- the edges can be stably extracted from the horizon near the vanishing point, which is in the distance with little change in the landscape, by setting the horizon reference area that references the horizon near the vanishing point as the daytime edge extraction area.
- the edges can be appropriately extracted from the pair of left and right road edge reference areas when there is difficulty extracting the edges of the horizon due to the presence of forests and woods on the horizon near the vanishing point; when there is difficulty extracting the edges of the horizon due to the setting sun or smears, the edges can be extracted by setting the pair of left and right road edge reference areas as the daytime edge extraction area, in addition to setting the horizon reference area.
- the pair of left and right road edge reference areas are set as the nighttime edge extraction area.
- the edge intensity calculation unit 36 extracts the edges of a subject from the edge extraction area that is set by the edge extraction area setting unit 35 and calculates the intensity of the edges in the edge extraction area. Specifically, the edge intensity calculation unit 36 first extracts the edges of a subject from the daytime edge extraction area, that is, from both the horizon reference area and the pair of left and right road edge reference areas, when an assessment has been made that the present is daytime by the day/night assessment unit 34; the edge intensity calculation unit extracts the edges of a subject from the nighttime edge extraction area, that is, from both the pair of left and right road edge reference areas, when an assessment has been made that the present is nighttime by the day/night assessment unit 34.
- the edge intensity calculation unit 36 is able to extract the edges of the subject from a captured image, for example, by using a Laplacian filter in a predetermined image range within the captured image that includes the edge extraction area.
- the edge intensity calculation unit 36 generates a histogram based on the intensity of the extracted edges after extracting the edges from the edge extraction area.
- the edge intensity calculation unit 36 generates a histogram for each of the daytime edge extraction areas, that is, for both the horizon reference area and the pair of left and right road edge reference areas, when an assessment has been made that the present is daytime by the day/night assessment unit 34; the edge intensity calculation unit generates a histogram for the nighttime edge extraction area, that is, for each of the pair of left and right road edge reference areas, when an assessment has been made that the present is nighttime by the day/night assessment unit 34.
- FIG. 15 is a view illustrating an example of a histogram based on the intensity of the edges.
- the edge intensity calculation unit 36 generates a histogram according to the intensity of the edges based on the edges in the edge extraction area, as illustrated in FIG. 15 .
- the edge intensity calculation unit 36 calculates the average value of the intensity of the edges in each edge extraction area as the edge intensity average value S ave based on the generated histogram, calculates the standard deviation ⁇ of the intensity of the edges in each edge extraction area, and calculates a value that is the sum of the edge intensity average value S ave and the standard deviation ⁇ of the intensity of the edges as the edge intensity deviation S ⁇ , as illustrated in FIG. 15 .
- the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ based on the value of the edge intensity deviation S ⁇ , as illustrated in FIG. 15 . Specifically, the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ as 0 when the value of the edge intensity deviation S ⁇ is a predetermined edge intensity lower limit value S min or smaller; when the edge intensity deviation S ⁇ is a predetermined edge intensity upper limit value S max or greater, the edge intensity calculation unit calculates the weighting of the edge intensity deviation S ⁇ as 1, as illustrated in FIG. 15 .
- the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ in the range from 0 to 1 according to the value of the edge intensity deviation S ⁇ when the value of the edge intensity deviation S ⁇ is within the range of the edge intensity lower limit value S min and the edge intensity upper limit value S max
- the weighting of the edge intensity deviation S ⁇ is calculated for the daytime edge extraction area, that is, for both the horizon reference area and the pair of left and right road edge reference areas; when an assessment has been made that the present is nighttime by the day/night assessment unit 34, the weighting of the edge intensity deviation S ⁇ is calculated for the nighttime edge extraction area, that is, for each of the pair of left and right road edge reference areas.
- the edge intensity lower limit value S min and the edge intensity upper limit value S max are unique values that are appropriately set by experimentation or by another means, and a different value is set depending on whether the present is daytime or nighttime. Specifically, both the edge intensity lower limit value S min and the edge intensity upper limit value S max are set to be relatively high values because, during the daytime, the luminance of the background is high and the edges of a subject are easily detected; both the edge intensity lower limit value S min and the edge intensity upper limit value S max are set to be relatively low values because, during the nighttime, the luminance of the background is low and the edges of the subject are not easily detected.
- the edge intensity calculation unit 36 then calculates the intensity of the edges in each edge extraction area based on the calculated weighting of the edge intensity deviation S ⁇ as the target edge intensity, as illustrated in FIG. 16.
- FIG. 16 is a view illustrating the relationship between the weighting of the edge intensity deviation S ⁇ and the target edge intensity.
- a lower limit value St min and an upper limit value St max are set for the target edge intensity; when the weighting of the edge intensity deviation S ⁇ is 0, a value of the lower limit value ST min is calculated as the target edge intensity; when the weighting of the edge intensity deviation S ⁇ is 1, a value of the upper limit value St max is calculated as the target edge intensity.
- the weighting of the edge intensity deviation S ⁇ and the target edge intensity are in a linear (proportional) relationship between the lower limit value St min and an intermediate value St mid , and they are in a relationship that is corrected by gamma conversion between the intermediate value St mid and the upper limit value St max , as illustrated in FIG. 16 .
- the edge intensity calculation unit 36 calculates a target edge intensity according to the weighting of the edge intensity deviation S ⁇ within a range from the lower limit value St min to the intermediate value St min when the weighting of the edge intensity deviation S ⁇ is from 0 to 0.5; the edge intensity calculation means calculates a target edge intensity according to the weighting of the edge intensity deviation S ⁇ within a value range from the intermediate value St mid to the upper limit value St max when the weighting of the edge intensity deviation S ⁇ is from 0.5 to 1 by using a map that illustrates the relationship between the edge intensity deviation S ⁇ and the target edge intensity, as that illustrated in FIG. 16 .
- the lower limit value St min and the upper limit value St max of the target edge intensity can be appropriately set by experimentation or by another means, and a different value is set depending on whether the present is daytime or nighttime.
- the edge intensity calculation unit 36 assesses whether the target edge intensity detected in the horizon reference area within the daytime edge extraction area is a predetermined value or greater and specifies the target edge intensity detected in the horizon reference area as a specific edge intensity that is used for setting the difference threshold th when the target edge intensity detected in the horizon reference area is a predetermined value or greater. On the other hand, when the target edge intensity detected in the horizon reference area is less than the predetermined value, the edge intensity calculation unit 36 specifies the highest target edge intensity from among the target edge intensities detected in the horizon reference area and the pair of left and right road edge reference areas as the specific edge intensity that is used for setting the difference threshold th.
- the predetermined value described above is appropriately set by experimentation or by another means; if the target edge intensity is equal to or greater than this predetermined value, a predetermined quantity of edges attributable to the horizon has been detected, and a value that facilitates the appropriate assessment of the turbidity of the lens will be set.
- the edges that are attributable to the horizon can be stably extracted from the horizon reference area, which is in the distance with little change in the landscape, by preferentially specifying the target edge intensity that is detected in the horizon reference area as the specific edge intensity; the turbidity of the lens can be assessed with a high degree of precision by using the target edge intensity attributable to the horizon that is extracted in this way.
- the lens turbidity can be calculated based on the target edge intensity in the left-side road edge reference area or the right-side road edge reference area even when there is difficulty extracting the edges from the horizon reference area due to the presence of forests and woods on the horizon in the horizon reference area or when there is difficulty extracting the edges from the horizon reference area due to the setting sun or smears; therefore, assessing the turbidity of the lens with a high degree of precision is possible.
- the edge intensity calculation unit 36 specifies the target edge intensity in the left-side road edge reference area from among the pair of left and right road edge reference areas that are set as the nighttime edge extraction areas as the specific edge intensity for setting the difference threshold th of a left-side detection area A2; then, the edge intensity calculation unit specifies the target edge intensity in the right-side road edge reference area as the specific edge intensity for setting the difference threshold th of the right-side detection area A1.
- appropriately setting a difference threshold th according to the light environment in each of the pair of left and right detection areas A1, A2 is possible by specifying the target edge intensity in the left-side road edge reference area as the specific edge intensity for setting the difference threshold th of the left-side detection area A2 and by specifying the target edge intensity in the right-side road edge reference area as the specific edge intensity for setting the difference threshold th of the right-side detection area A1; as a result, the detection of a three-dimensional object can be carried out with a high degree of precision.
- the edge intensity calculation unit 36 then stores the specific edge intensity specified in this way in the memory (not diagrammed) of the computer 30. Additionally, the edge intensity calculation unit 36 has repeatedly calculated the specific edge intensity at a predetermined cycle and will calculate the final intensity of the edges in the edge extraction area with consideration given to the specific edge intensities that have been calculated in the past as the final edge intensity. For example, of the plurality of specific edge intensities that are stored in the memory, the edge intensity calculation unit 36 may decrease the weighting more for the specific edge intensities that have been more recently stored and calculate the moving average value of the plurality of specific edge intensities that have been calculated within a predetermined period of time as the final edge intensity.
- the threshold value changing unit 37 changes the difference threshold th described above based of the final edge intensity that is calculated by the edge intensity calculation unit 36.
- the threshold value changing unit 37 determines that the lens is more clouded the lower the final edge intensity and changes the difference threshold th in the detection areas A1, A2 to a lower value, as illustrated in FIG. 17 .
- the threshold value changing unit 37 determines that the lens is less clouded the higher the final edge intensity becomes and changes the difference threshold th in the detection areas A1, A2 to a higher value. Accordingly, noise can be effectively suppressed; as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- FIG. 17 is a view illustrating the relationship between the difference threshold th and the edge intensity.
- the threshold value changing unit 37 changes the relationship between the difference threshold th and the final edge intensity so that the difference threshold th is calculated at a relatively high value even when the final edge intensity is relatively low, as compared to when the surrounding is not pitch-dark, as illustrated in FIG. 17 .
- the threshold value changing unit 37 is able to assess that the surrounding is pitch dark when the luminance of the entire captured image is equal to or less than a predetermined luminance with which a determination can be made that the surrounding is pitch dark.
- FIG. 18 is a flowchart illustrating the operation for detecting an adjacent vehicle according to the first embodiment.
- data of a captured image is acquired by the computer 30 from the camera 10 (Step S101), and data of a bird's-eye view image PB t is generated (Step S102) by the viewpoint conversion unit 31 based on the data of the captured image thus acquired, as illustrated in FIG. 18 .
- the alignment unit 32 aligns the bird's-eye view image PB t data and the bird's-eye view image PB t-1 data at a single moment prior and generates differential image PD t data (Step S103). Specifically, the alignment unit 32 takes the absolute value of the difference in the pixel values of the bird's-eye view images PB t and PB t-1 ; when the absolute value is equal to or greater than a predetermined threshold value th, the pixel values of the differential image PD t are set to "1;" when the absolute value is less than a predetermined threshold value th, the pixel values of the differential image PD t are set to "0.” There are cases in which the difference threshold value th for calculating the pixel values of the differential image PD t is changed in the threshold value changing process mentioned below; in the case that the difference threshold value th is changed, the changed difference threshold value th will be used in this Step S103.
- the three-dimensional object detection unit 33 then counts the number of difference pixels DP having
- the three-dimensional object detection unit 33 determines whether the peak of the differential waveform DW t is at a threshold value ⁇ or greater (Step S105).
- the peak of the differential waveform DW t is not at the threshold value ⁇ or greater, in particular, when there is essentially no difference, the thought is that a three-dimensional object is not present in the captured image.
- Step S105 No
- the three-dimensional object detection unit 33 determines that a three-dimensional object is not present and that an adjacent vehicle V2 is not present (Step S 114). The operation then returns to Step S101 and repeats the operation illustrated in FIG. 18 .
- Step S105 Yes
- Step S106 the three-dimensional object detection unit 33 divides the differential waveform DW t into a plurality of small areas DWt1 to DW tn .
- the three-dimensional object detection unit 33 next weights each of the small areas DW t1 to DW tn (Step S107), calculates the offset amount for each of the small areas DW t1 to DW tn (Step S108), and generates a histogram with consideration given to the weightings (Step S109).
- the three-dimensional object detection unit 33 calculates the relative travel distance, which is the travel distance of the three-dimensional object in relation to the host vehicle V1, based on the histogram (Step S110). Next, the three-dimensional object detection unit 33 calculates the absolute travelling speed of the three-dimensional object from the relative travel distance (Step S111). At this time, the three-dimensional object detection unit 33 time-differentiates the relative travel distance to thereby calculate the relative travelling speed, adds the host vehicle speed detected by the vehicle speed sensor 20, and calculates the relative travelling speed.
- Step S112 No
- the three-dimensional object detection unit 33 determines that an adjacent vehicle V2 is not present in an adjacent lane (Step S114). The operation then returns to Step S101 and repeats the operation illustrated in FIG. 18 .
- the detection areas A1, A2 are to the left and right of the rear of the host vehicle V1, and focus is placed on whether the host vehicle V1 may possibly make contact with another object should a lane change be made. Accordingly, the operation of Step S112 is implemented.
- the system in the present embodiment is actuated on an expressway, when the speed of an adjacent vehicle V2 is less than 10 km/h, there would rarely be a problem even if an adjacent vehicle V2 were to be present because the adjacent vehicle V2 would be positioned far behind the host vehicle V1 when a lane change is made.
- Step S112 determines if an adjacent vehicle V2 can pose a problem when a lane change is made.
- Step S112 a determination is made whether the absolute travelling speed of the adjacent vehicle V2 is 10 km/h or greater and whether the relative travelling speed of the adjacent vehicle V2 in relation to the host vehicle V1 is +60 km/h or less, thereby obtaining the following effect.
- a possible case is that the absolute travelling speed of a stationary object is detected to be several kilometers per hour, depending on the attachment error of the camera 10. Accordingly, determining whether the speed is 10 km/h or greater enables the reduction of the possibility that the stationary object will be determined to be an adjacent vehicle V2.
- the relative speed of an adjacent vehicle V2 in relation to the host vehicle V1 will be detected to be in excess of +60 km/h due to noise. Accordingly, determining whether the relative speed is +60 km/h or less enables the reduction of the possibility of an erroneous detection due to noise.
- Step S112 a determination can be made as to whether the absolute travelling speed of the adjacent vehicle V2 is not negative or not 0 km/h.
- a warning sound may be emitted to the driver of the host vehicle, or a corresponding warning may be displayed by a predetermined display device when an adjacent vehicle V2 is detected in Step S113.
- FIG. 19 is a flowchart illustrating the threshold value changing process according to the first embodiment.
- the threshold value changing process described below is carried out in parallel with the adjacent vehicle detection process illustrated in FIG. 18 , and the difference threshold th that is set by this threshold value changing process is applied as the difference threshold th in the adjacent vehicle detection process illustrated in FIG. 18 .
- Step S201 a determination is made regarding whether or not an adjacent vehicle V2 is being detected by the computer 30, as illustrated in FIG. 19 .
- the computer 30 determines that an adjacent vehicle is being detected and waits in Step S201; when a determination is made that an adjacent vehicle V2 is not being detected, the operation proceeds to Step S202.
- Step S202 a determination is made whether the present is nighttime or daytime by the day/night assessment unit 34.
- the day/night assessment unit 34 can calculate the average luminance of the entire captured image and determine that the present is daytime when the calculated average luminance is a predetermined value or greater; when the calculated average luminance is less than the predetermined value, the day/night assessment unit can assess that the present is nighttime.
- the operation proceeds to Step S203; when an assessment has been made that the present is nighttime, the operation proceeds to Step S214.
- the threshold value changing process when an assessment has been made that the present is daytime will be described below.
- Step S203 the daytime edge extraction area is set by the edge extraction area setting unit 35.
- the edge extraction area setting unit 35 sets the horizon reference area that references the horizon near the vanishing point and the pair of left and right road edge reference areas that reference the road edge as the daytime edge extraction areas, as illustrated in FIG. 13
- Step S204 the extraction of the edges of the subject is carried out by the edge intensity calculation unit 36 in the daytime edge extraction area, that is, in the horizon reference area and each of the pair of left and right road edge reference areas.
- Step S205 a histogram is generated based on the intensity of the edges by the edge intensity calculation unit 36, based on the edges extracted in Step S204, for the horizon reference area and each of the pair of left and right road edge reference areas, which are the daytime edge extraction areas, as illustrated in FIG. 15 .
- Step S206 the edge intensity calculation unit 36 calculates an average value of the intensity of the edges for the horizon reference area and each of the pair of left and right road edge reference areas as the edge intensity average value S ave based on the histogram generated in Step S205, calculates the standard deviation ⁇ of the intensity of the edges, and calculates a value that is the sum of the edge intensity average value S ave and the standard deviation ⁇ of the intensity of the edges as the edge intensity deviation S ⁇ , as illustrated in FIG. 15 .
- the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ for the horizon reference area and each of the pair of left and right road edge reference areas based on the edge intensity deviation S ⁇ calculated in Step S206. Specifically, the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ as 0 when the value of the edge intensity deviation S ⁇ is an edge intensity lower limit value S min or smaller; the edge intensity calculation unit calculates the weighting of the edge intensity deviation S ⁇ as 1 when the edge intensity deviation S ⁇ is an edge intensity upper limit value S max or greater, as illustrated in FIG. 15 .
- the edge intensity calculation unit 36 calculates the weighting of the edge intensity deviation S ⁇ in the range from 0 to 1 according to the value of the edge intensity deviation S ⁇ when the value of the edge intensity deviation S ⁇ is within the range of the edge intensity lower limit value S min to the edge intensity upper limit value S max .
- Step S208 the edge intensity calculation unit 36 calculates the weighting of the intensity of the edges for the horizon reference area and each of the pair of left and right road edge reference areas as the target edge intensity, based on the edge intensity deviation S ⁇ calculated in Step S207.
- the edge intensity calculation unit 36 can calculate the target edge intensity based on the weighting of the edge intensity deviation S ⁇ by using a map that illustrates the relationship between the weighting of the edge intensity deviation S ⁇ and the target edge intensity, as illustrated in FIG. 16
- Step S209 the edge intensity calculation unit 36 determines whether the target edge intensity in the horizon reference area, from among the target edge intensities in each area of the daytime edge extraction areas calculated in Step S208, is a predetermined value or greater.
- the operation proceeds to Step S210, and the edge intensity calculation unit 36 specifies the target edge intensity in the horizon reference area from among the daytime edge extraction areas as the specific edge intensity.
- the operation proceeds to Step S211, and the edge intensity calculation unit 36 specifies the target edge intensity with the highest value from among the target edge intensities in the horizon reference area and the pair of left and right road edge reference areas, which are the daytime edge extraction areas, as the specific edge intensity.
- the edge intensity calculation unit 36 calculates the final intensity of the edges in the edge extraction area as the final edge intensity based on the specific edge intensity specified in Step S210 or Step S211.
- the edge intensity calculation unit 36 can acquire the specific edge intensities calculated in the past from the memory (not diagrammed) of the computer 30, can decrease the weighting more for the specific edge intensities that have been more recently stored from among the plurality of specific edge intensities that have been calculated between the current time and a predetermined time in the past, and can calculate the moving average value of the plurality of specific edge intensities as the final edge intensity.
- the threshold value changing unit 37 changes the difference threshold th in the pair of left and right detection areas A1, A2 based on the final edge intensity calculated in Step S212. Specifically, the threshold value changing unit 37 determines that the lens is more clouded the lower the final edge intensity and changes the difference threshold th in the detection areas A1, A2 to a lower value, as illustrated in FIG. 17 . Therefore, detecting a three-dimensional object even when the lens is clouded becomes easier; as a result, appropriately detecting an adjacent vehicle V2 is possible. On the other hand, the threshold value changing unit 37 determines that the lens is less clouded as the final edge intensity becomes higher and changes the difference threshold th in the detection areas A1, A2 to a higher value. Accordingly, the generation of noise is suppressed, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- the threshold value changing unit 37 sets the difference threshold th to be the same value as calculated, based on the final edge intensity, to the pair of left and right detection areas A1, A2, as in Step S213.
- the calculated difference threshold th can be set as the difference threshold th in the pair of left and right detection areas A1, A2.
- the difference threshold th can be set for both the right-side detection area A1 and the left-side detection area A2; as a result, appropriately detecting a three-dimensional object in the right-side detection area A1 and the left-side detection area A2 is possible.
- Step S214 the nighttime edge extraction area is set by the edge extraction area setting unit 35. Specifically, the edge extraction area setting unit 35 sets a left-side road edge reference area and a right-side road edge reference area, which reference the left and right road edges, as the nighttime edge extraction areas, as illustrated in FIG. 11 .
- Step S215 to Step S219 the same operation as in Steps S204 to S208 is carried out in the left-side road edge reference area and the right-side road edge reference area that have been set as the nighttime edge extraction areas.
- the edges of the subject are extracted (Step S215), and histograms corresponding to each of the pair of left and right road edge reference areas are generated based on the edges that are extracted from the pair of left and right road edge reference areas, as illustrated in FIG. 15 (Step S216).
- the edge intensity deviation S ⁇ is calculated for each of the pair of left and right road edge reference areas based on the generated histograms (Step S217), and the weightings for these edge intensity deviations S ⁇ are calculated (Step S218). Then, as illustrated in FIG. 16 , the intensities of the edges in the left-side road edge reference area and the right-side road edge reference area that are set as the nighttime edge extraction areas are calculated as the target edge intensities, based on the calculated weightings of the edge intensity deviations S ⁇ (Step S219).
- the edge intensity calculation unit 36 specifies the specific edge intensity. Specifically, the edge intensity calculation unit 36 specifies the target edge intensity in the left-side road edge reference area from among the pair of left and right road edge reference areas that have been set as the nighttime edge extraction areas as the specific edge intensity for setting the difference threshold th in the left-side detection area A2; then, the edge intensity calculation unit specifies the target edge intensity in the right-side road edge reference area as the specific edge intensity for setting the difference threshold th in the right-side detection area A1.
- the specified specific edge intensities are stored in the memory (not diagrammed) of the computer 30 along with the specified time.
- the edge intensity calculation unit 36 calculates the final edge intensity. For example, during the nighttime, the edge intensity calculation unit 36 can acquire the specific edge intensities calculated in the past from the memory (not diagrammed) of the computer 30, can decrease the weighting more for the specific edge intensities that have been more recently stored from among the plurality of specific edge intensities that have been calculated between the current time and a predetermined time in the past, and can calculate the moving average value of the plurality of specific edge intensities as the final edge intensity.
- the edge intensity calculation unit 36 calculates the final edge intensity for setting the difference threshold th in the right-side detection area A1 based on the specific edge intensity for setting the difference threshold th in the right-side detection area A1, and calculates the final edge intensity for setting the difference threshold th in the left-side detection area A2, based on the specific edge intensity for setting the difference threshold th in the left-side detection area A2.
- the threshold value changing unit 37 sets the difference threshold th in the right-side detection area A1 from among the pair of left and right detection areas A1, A2; in Step S223, the threshold value changing unit 37 sets the difference threshold in the left-side detection area A2 from among the pair of left and right detection areas A1, A2. Specifically, the threshold value changing unit 37 determines that the lens is more clouded the lower that the final edge intensity calculated in Step S221 is and changes the difference threshold th in the detection areas A1, A2 to a lower value, as illustrated in FIG. 17 . Therefore, detecting a three-dimensional object even when the lens is clouded becomes easier, and as a result, appropriately detecting an adjacent vehicle V2 is possible.
- the threshold value changing unit 37 determines that the lens is less clouded the higher the final edge intensity is and changes the difference threshold th in the detection areas A1, A2 to a higher value. Accordingly, the generation of noise is suppressed, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- the threshold value changing unit 37 calculates the difference threshold th in the right-side detection area A1, based on the final edge intensity in the right-side road edge reference area calculated in Step S221, and sets the difference threshold th in the right-side detection area A1, as illustrated in FIG. 17 .
- the threshold value changing unit 37 calculates the difference threshold th in the left-side detection area A2, based on the final edge intensity in the left-side road edge reference area calculated in Step S221, and sets the difference threshold th in the left-side detection area A2, as illustrated in FIG. 17 .
- the threshold value changing unit 37 sets the difference threshold th in the left-side detection area A1 and the difference threshold th in the right-side detection area A2 separately in this manner when an assessment is being made that the present is nighttime. Accordingly, appropriately detecting a three-dimensional object even when the light environment differs in the right side and the left side of the host vehicle V1 at night is possible.
- the threshold value changing unit 37 changes the relationship between the difference threshold th and the target edge intensity so that the difference threshold th is calculated at a relatively high value even when the final edge intensity is relatively low, when compared to when the surrounding is not pitch-dark, as illustrated by the broken line in FIG. 17 .
- an area from which a predetermined quantity of edges can be expected to be extracted is set as an edge extraction area, and a difference threshold th is calculated based on the intensity of the edges in the edge extraction area. Specifically, a determination is made that the lens is more clouded as the intensity of the edges (the final edge intensity) in the edge extraction area decreases, and the difference threshold th is set to a low value, as illustrated in FIG. 17 . As a result, detecting a three-dimensional object becomes easier, and appropriately detecting a three-dimensional object even when the lens is clouded is possible.
- the lens is less clouded as the intensity of the edges (the final edge intensity) in the edge extraction area increases, and the difference threshold th is set to a high value, as illustrated in FIG. 17 .
- the difference thresholds th when an assessment has been made that the present is daytime, the difference thresholds th with the same value are set in the pair of left and right detection areas A1, A2; when an assessment has been made that the present is nighttime, the difference thresholds th are set according to the light environment of each of the pair of left and right detection areas A1, A2. Accordingly, in the first embodiment, the difference in the difference thresholds th between the pair of left and right detection areas A1, A2 when an assessment has been made that the present is daytime becomes equal to or less than the difference in the difference thresholds th between the pair of left and right detection areas A1, A2 when an assessment has been made that the present is nighttime.
- the difference in the light environment between the right-side detection area A1 and the left-side detection area A2 will be determined to be little; therefore, appropriate difference thresholds th based on the final edges can be set for both the right-side detection area A1 and the left-side detection area A2, thereby allowing for an appropriate detection of a three-dimensional object in the right-side detection area A1 and the left-side detection area A2.
- FIG. 20 is a block view illustrating the details of the computer 30a according to the second embodiment.
- the three-dimensional object detection device 1a according to the second embodiment is provided with a camera 10 and a computer 30a, as illustrated in FIG. 20 .
- the computer 30a is provided with a viewpoint conversion unit 31, a luminance difference calculation unit 38, an edge line detection unit 39, a three-dimensional object detection unit 33a, a day/night assessment unit 34, an edge extraction area setting unit 35, an edge intensity calculation unit 36, and a threshold value changing unit 37a.
- the configuration of the three-dimensional object detection device 1a according to the second embodiment is described below.
- the configurations of the viewpoint conversion unit 31, the day/night assessment unit 34, the edge extraction area setting unit 35, and the edge intensity calculation unit 36 are the same as in those in the first embodiment; therefore, the descriptions thereof have been omitted.
- FIG. 21 is a view illustrating the image range of the camera 10 in FIG. 20 ;
- FIG. 21 (a) is a plan view, and
- FIG. 21(b) is a perspective view in real space rearward from the host vehicle V1.
- the camera 10 is set to a predetermined view angle a, and the rear side of the host vehicle V1 that is included in the predetermined view angle a is captured, as illustrated in FIG. 21(a) .
- the view angle a of the camera 10 is set so that the adjacent lanes are included in the capture range of the camera 10 in addition to the lane in which the host vehicle V1 is driving, in the same manner as that illustrated in FIG. 2 .
- the detection areas A1, A2 in the present example are trapezoidal in a plan view (a bird's-eye view state), and the position, the size, and the shape of the detection areas A1, A2 are determined based on the distances d 1 to d 4
- the detection areas A1, A2 of the example illustrated in the drawing are not limited to being trapezoidal, and they may also be rectangular or another shape in a bird's-eye view state, as illustrated in FIG. 2 .
- the distance d1 is the distance from the host vehicle V1 to the ground lines L1, L2.
- the ground lines L1, L2 refer to lines through which a three-dimensional object, which is present in a lane adjacent to the lane in which the host vehicle V1 is driving, is in contact with the ground.
- an objective is to detect an adjacent vehicle V2 or the like (including two-wheel vehicles or the like) driving in the left or right lane behind the host vehicle V1 and adjacent to the lane of the host vehicle V1.
- the distance d1 which is the position of the ground lines L1, L2 of the adjacent vehicle V2 can be decided so as to be substantially fixed from the distance d11 from the host vehicle V1 to a white line W and from the distance d12 from the white line W to the position in which the adjacent vehicle V2 is predicted to drive.
- the distance d1 is not limited to being fixed and may be variable.
- the computer 30a recognizes the position of the white line W in relation to the host vehicle V1 using white line recognition or another technique, and the distance d11 is determined based on the position of the recognized white line W.
- the distance d1 is thereby variably set using the determined distance d11.
- the position in which the adjacent vehicle V2 is driving (the distance d12 from the white line W) and the position in which the host vehicle V1 is driving (the distance d11 from the white line W) is mostly predictable, and the distance d1 is fixed.
- a distance d2 is the distance extending from the rear end part of the host vehicle V1 in the vehicle traveingl direction.
- the distance d2 is determined so that the detection areas A1, A2 are accommodated within at least the view angle a of the camera 10.
- the distance d2 is set so as to be in contact with a range partitioned within the view angle a.
- the distance d3 indicates the length of the detection areas A1, A2 in the vehicle traveingl direction.
- the distance d3 is determined based on the size of the three-dimensional object to be detected.
- the object to be detected is an adjacent vehicle V2 or the like; therefore, the distance d3 is set to a length that includes the adjacent vehicle V2.
- the distance d4 indicates the height, which has been set so that the tires of the adjacent vehicle V2 or the like are included in real space, as illustrated in FIG. 21(b) .
- the distance d4 is the length illustrated in FIG. 21(a) .
- the distance d4 may also be a length that does not include the lanes further adjacent to the left and right adjacent lanes in the bird's-eye view image (in particular, the adjacent-adjacent lanes that are two lanes away).
- the distances d1 to d4 are determined, and the position, the size, and the shape of the detection areas A1, A2 are thereby determined. More specifically, the position of the top side b1 of the detection areas A1, A2 that form a trapezoid is determined by the distance d1. The starting position C1 of the top side b1 is determined by the distance d2. The end position C2 of the top side b1 is determined by the distance d3. The lateral side b2 of the detection areas A1, A2 that form a trapezoid is determined by a straight line L3 that extends from the camera 10 toward the starting position C1.
- the lateral side b3 of the detection areas A1, A2 that form a trapezoid is determined by a straight line L4 that extends from the camera 10 toward the end position C2.
- the position of the lower side b4 of the detection areas A1, A2 that form a trapezoid is determined by the distance d4.
- the areas surrounded by the sides b1 to b4 are the detection areas A1, A2.
- the detection areas A1, A2 are regular squares (rectangles) in the real space that is rear of the host vehicle V1, as illustrated in FIG. 21(b) .
- the luminance difference calculation unit 38 calculates luminance differences in the bird's-eye view image data, which has undergone viewpoint conversion by the viewpoint conversion unit 31, in order to detect the edges of a three-dimensional object included in the bird's-eye view image. For each of a plurality of positions along a perpendicular imaginary line that extends along the perpendicular direction in real space, the luminance difference calculation unit 38 calculates the luminance difference between two pixels near each position.
- the luminance difference calculation unit 38 is capable of calculating the luminance difference by a method for setting a single perpendicular imaginary line that extends in the perpendicular direction in real space or by a method for setting two perpendicular imaginary lines.
- the luminance difference calculation unit 38 sets a first perpendicular imaginary line that corresponds to a line segment that extends in the perpendicular direction in real space and a second perpendicular imaginary line that is different from the first perpendicular imaginary line and that corresponds to the line segment extending in the perpendicular direction in real space.
- the luminance difference calculation unit 38 determines the luminance difference between a point on the first perpendicular imaginary line and a point on the second perpendicular imaginary line in continuous fashion along the first perpendicular imaginary line and the second perpendicular imaginary line. The operation of the luminance difference calculation unit 38 is described in detail below.
- the luminance difference calculation unit 38 sets a first perpendicular imaginary line La (hereinafter referred to as the attention line La) that corresponds to a line segment extending in the perpendicular direction in real space and that passes through the detection area A1, as illustrated in FIG. 22(a) .
- the luminance difference calculation unit 38 sets a second perpendicular imaginary line Lr (hereinafter referred to as the reference line Lr) that is different from the attention line La, corresponds to the line segment extending in the perpendicular direction in real space, and passes through the detection area A1.
- the reference line Lr is set in a position at a distance from the attention line La by a predetermined distance in real space.
- the lines that correspond to the line segments extending in the perpendicular direction in real space are lines that spread out in the radial direction from the position Ps of the camera 10 in a bird's-eye view image. These lines spreading out in the radial direction are lines that follow the collapsing direction of the three-dimensional object when converted into a bird's-eye view.
- the luminance difference calculation unit 38 sets an attention point Pa on the attention line La (a point on the first perpendicular imaginary line).
- the luminance difference calculation unit 38 sets a reference point Pr on the reference line Lr (a point on the second perpendicular imaginary line).
- the attention line La, the attention point Pa, the reference line Lr, and the reference point Pr have the relationship in real space that is illustrated in FIG. 22(b) .
- the attention line La and the reference line Lr are lines extending in the perpendicular direction in real space
- the attention point Pa and the reference point Pr are points set to be substantially the same height in real space.
- the attention point Pa and the reference point Pr are not necessarily required to be rigorously kept at the same height, and a certain amount of error that allows for the attention point Pa and the reference point Pr to be deemed to be at the same height is allowed.
- the luminance difference calculation unit 38 determines the luminance difference between the attention point Pa and the reference point Pr. If the luminance difference between the attention point Pa and the reference point Pr is great, there is a possibility that an edge is present between the attention point Pa and the reference point Pr.
- a perpendicular imaginary line is set as a line segment extending in the perpendicular direction in real space in relation to the bird's-eye view image in order to detect a three-dimensional object present in the detection areas A1, A2. Therefore, there is a high possibility that there is an edge of a three-dimensional object in the location where the attention line La has been set when the luminance difference between the attention line La and the reference line Lr is high. Accordingly, the edge line detection unit 39 illustrated in FIG. 20 detects an edge line based on the luminance difference between the attention point Pa and the reference point Pr.
- FIG. 23 is a view showing the detailed operation of the luminance difference calculation unit 38.
- FIG. 23(a) illustrates a bird's-eye view image of the bird's-eye view state
- FIG. 23(b) is an enlarged view of a part B1 of the bird's-eye view image illustrated in FIG. 23(a) .
- FIG. 23 only the detection area A1 is illustrated and described, but the luminance difference is calculated using the same procedure for detection area A2.
- the adjacent vehicle V2 When the adjacent vehicle V2 is being displayed in the captured image captured by the camera 10, the adjacent vehicle V2 appears in the detection area A1 in the bird's-eye view image, as illustrated in FIG. 23(a) .
- the attention line La is set on a rubber portion of a tire of the adjacent vehicle V2 in the bird's-eye view image in FIG. 23(b) , as illustrated in the enlarged view of area B1 in FIG. 23(a) .
- the luminance difference calculation unit 38 sets the reference line Lr.
- the reference line Lr is set along the perpendicular direction in a position set at a predetermined distance in real space from the attention line La.
- the reference line Lr is set in a position at a distance of 10 cm away in real space from the attention line La.
- the reference line Lr is thereby set on the wheel of the tire of the adjacent vehicle V2 set, for example, at a distance that corresponds to 10 cm from the rubber of the tire of the adjacent vehicle V2 in the bird's-eye view image.
- the luminance difference calculation unit 38 sets a plurality of attention points Pa1 to PaN on the attention line La.
- attention point Pai when indicating an arbitrary point
- An arbitrary number of attention points Pa may be set on the attention line La.
- N attention points Pa are set on the attention line La.
- the luminance difference calculation unit 38 subsequently sets the reference points Pr1 to PrN so that they have the same height as the attention points Pa1 to PaN in real space.
- the luminance difference calculation unit 38 calculates the luminance difference between the attention point Pa and the reference point Pr pairs at the same height.
- the luminance difference calculation unit 38 thereby calculates the luminance difference between two pixels for each of the plurality of positions (1 - N) along the perpendicular imaginary line extending in the perpendicular direction in real space.
- the luminance difference calculation unit 38 calculates the luminance difference between, for example, a first attention point Pa1 and a first reference point Pr1 and calculates the luminance difference between a second attention point Pa2 and a second reference point Pr2.
- the luminance difference calculation unit 38 thereby determines the luminance difference in a continuous fashion along the attention line La and the reference line Lr. In other words, the luminance difference calculation unit 38 sequentially determines the luminance difference between the third to N th attention points Pa3 to PaN and the third to N th reference points Pr3 to PrN.
- the luminance difference calculation unit 38 repeats the operation of setting the above-described reference line Lr, setting the attention point Pa, setting the reference point Pr, and calculating the luminance difference while shifting the attention line La within the detection area A1. In other words, the luminance difference calculation unit 38 repeatedly executes the above-described operation while changing the positions of the attention line La and the reference line Lr by the same distance in real space along the direction in which the ground line L1 extends.
- the luminance difference calculation unit 38 for example, sets the line that was the reference line Lr in the previous operation to be the attention line La, sets the reference line Lr in relation to the attention line La, and sequentially determines the luminance difference.
- determining the luminance difference from the attention point Pa on the attention line La and the reference point Pr on the reference line Lr, which are at substantially the same height in real space allows the luminance difference to be distinctly detected when an edge extending in the perpendicular direction is present.
- the precision for detecting a three-dimensional object can be enhanced without the operation for detecting the three-dimensional object being affected even when the three-dimensional object is enlarged in accordance with the height from the road surface by conversion into a bird's-eye view image in order to compare the luminance between the perpendicular imaginary lines extending in the perpendicular direction in real space.
- the edge line detection unit 39 detects the edge line from the continuous luminance difference calculated by the luminance difference calculation unit 38.
- the first attention point Pa1 and the first reference point Pr1 are positioned at the same tire portion, and the luminance difference is therefore small.
- the second to sixth attention points Pa2 to Pa6 are positioned at the rubber portions of the tire, and the second to sixth reference points Pr2 to Pr6 are positioned at the wheel portion of the tire. Therefore, the luminance difference between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 is great. Accordingly, the edge line detection unit 39 is capable of detecting that an edge is present between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 where the luminance difference is great.
- the edge line detection unit 39 first assigns an attribute to the i th attention point Pai from the luminance difference between the i th attention point Pai (coordinates (xi, yi)) to the i th reference point Pri (coordinates (xi', yi')) in accordance with formula 1 noted below.
- t represents an edge threshold value
- I(xi, yi) represents the luminance value of the i th attention point Pai
- I(xi', yi') represents the luminance value of the i th reference point Pri.
- the attribute s(xi, yi) of the attention point Pai is '1' when the luminance value of the attention point Pai is greater than the luminance value obtained by adding the threshold value t to the reference point Pri.
- the attribute s(xi, yi) of the attention point Pai is '-1' when the luminance value of the attention point Pai is less than the luminance value obtained by subtracting the threshold value t from the reference point Pri.
- the attribute s(xi, yi) of the attention point Pai is '0' when the luminance value of the attention point Pai and the luminance value of the reference point Pri are in a relationship other than that stated above.
- the edge threshold value t is changed by the threshold value changing unit 37a mentioned below; when the edge threshold value t is changed by the threshold value changing unit 37a, the attribute s(xi, yi) of the attention point Pai is detected using the edge threshold value t that is changed by the threshold value changing unit 37a.
- the continuity c(xi, yi) is 1' when the attribute s(xi, yi) of the attention point Pai and the attribute s(xi + 1, yi + 1) of the adjacent attention point Pai + 1 are the same.
- the continuity c(xi, yi) is '0' when the attribute s(xi, yi) of the attention point Pai and the attribute s(xi + 1, yi + 1) of the adjacent attention point Pai + 1 are not the same.
- the edge line detection unit 39 determines the sum of the continuities c of all of the attention points Pa on the attention line La.
- the edge line detection unit 39 divides the sum of the continuities c thus determined by the number N of attention points Pa to thereby normalize the continuity c.
- the edge line detection unit 39 determines the attention line La to be an edge line when the normalized value has exceeded a threshold value ⁇ .
- the threshold value ⁇ is set in advance by experimentation or by another means.
- the edge line detection unit 39 determines whether the attention line La is an edge line based on formula 3 noted below. The edge line detection unit 39 then determines whether all of the attention lines La drawn on the detection area A1 are edge lines. ⁇ c xi , yi / N > ⁇
- FIG. 24 is a view illustrating an image example showing the processing of the edge line detection unit 39.
- This image example is an image in which a first stripe pattern 101, indicating a stripe pattern in which the areas of high luminance and the areas of low luminance are repeated, and a second stripe pattern 102, indicating a stripe pattern in which the areas of low luminance and the areas of high luminance are repeated, are adjacent to each other. Also, in this image example, the areas with the first stripe pattern 101 in which the luminance is high and the areas with the second stripe pattern 102 in which the luminance is low are adjacent to each other; also, the areas with the first stripe pattern 101 in which the luminance is low and the areas with the second stripe pattern 102 in which the luminance is high are adjacent to each other.
- the location 103 positioned on the boundary between the first stripe pattern 101 and the second stripe pattern 102 tends not to be perceived as an edge by human senses.
- the location 103 is recognized as an edge when an edge is detected only by the luminance difference.
- the edge line detection unit 39 assesses the location 103 to be an edge line only when there is continuity in the attributes of the luminance difference. Therefore, the edge line detection unit 39 is capable of suppressing an erroneous assessment in which the location 103, which is not recognized as an edge line by human senses, is recognized to be an edge line, and the edges can be detected by human senses.
- the three-dimensional object detection unit 33a detects a three-dimensional object based on the quantity of edge lines detected by the edge line detection unit 39.
- the three-dimensional object detection device 1a detects an edge line extending in the perpendicular direction in real space. Detecting many edge lines extending in the perpendicular direction indicates that there is a high possibility that a three-dimensional object is present in the detection areas A1, A2. Accordingly, the three-dimensional object detection unit 33a detects a three-dimensional object based on the quantity of edge lines detected by the edge line detection unit 39.
- the three-dimensional object detection unit 33a determines whether the quantity of edge lines detected by the edge line detection unit 39 is a predetermined threshold value ⁇ or greater; when the quantity of edge lines is a predetermined threshold value ⁇ or greater, the edge lines detected by the edge line detection unit 39 are determined to be the edge lines of a three-dimensional object.
- the three-dimensional object detection unit 33a assesses whether the edge lines detected by the edge line detection unit 39 are correct.
- the three-dimensional object detection unit 33a assesses whether a change in the luminance of the edge lines is a predetermined threshold value tb or greater along the edge lines of the bird's-eye view image.
- a threshold value tb or greater When the change in the luminance of the edge lines in the bird's-eye view image is a threshold value tb or greater, the edge lines are determined to have been detected by an erroneous assessment.
- the threshold value tb is set in advance by experimentation or by another means.
- FIG. 25 is a view illustrating the luminance distribution on the edge line;
- FIG. 25(a) illustrates the edge line and the luminance distribution when an adjacent vehicle V2 as a three-dimensional object is present in the detection area A1
- FIG. 25(b) illustrates the edge line and the luminance distribution when a three-dimensional object is not present in the detection area A1.
- a the attention line La set on the tire rubber portion of the adjacent vehicle V2 has been determined to be an edge line in the bird's-eye view image.
- the change in luminance on the attention line La in the bird's-eye view image is gradual. This is due to the image captured by the camera 10 being converted in viewpoint into a bird's-eye view image, whereby the tire of the adjacent vehicle is enlarged within the bird's-eye view image.
- the attention line La set in the white character portion "50" drawn on the road surface in the bird's-eye view image is assumed to have been erroneously assessed to be an edge line, as illustrated in FIG. 25(b) .
- the change in the luminance of the attention line La in the bird's-eye view image has considerable undulations. This is because the road and other portions of low luminance are mixed with the portions of high luminance in the white characters on the edge line.
- the three-dimensional object assessment unit 33a assesses whether an edge line has been detected by an erroneous assessment based on the differences in the luminance distribution on the attention line La as described above. For example, a three-dimensional object included in a captured image tends to appear in an enlarged state in a bird's-eye view image when the captured image acquired by the camera 10 is converted into a bird's-eye view image. As described above, when the tire of an adjacent vehicle V2 is enlarged, the changes in the luminance of the bird's-eye view image in the enlarged direction tend to be small because the tire as a single location is enlarged.
- the three-dimensional object detection unit 33a determines that the edge line has been detected by an erroneous assessment when the change in luminance along the edge line is at a predetermined threshold value tb or greater and determines that the edge line is not attributable to a three-dimensional object.
- the three-dimensional object detection unit 33a determines that an edge line is the edge line of a three-dimensional object and determines that a three-dimensional object is present when the changes in luminance along the edge line are less than a predetermined threshold value tb.
- the three-dimensional object detection unit 33a calculates the change in luminance of the edge line using formula 4 or 5 noted below.
- the change in luminance of the edge line corresponds to the evaluation value in real space in the perpendicular direction.
- Formula 4 evaluates the luminance distribution using the total value of the square of the difference between the i th luminance value I(xi, yi) and the adjacent i th + 1 luminance value I(xi + 1, yi + 1) on the attention line La.
- Formula 5 evaluates the luminance distribution using the total value of the absolute value of the difference between the i th luminance value I(xi, yi) and the adjacent i th +1 luminance value I(xi + 1, yi + 1) on the attention line La.
- the attribute b(xi, yi) of the attention point Pa(xi, yi) is '1' when the absolute value of the luminance difference between the luminance value of the attention point Pai and the luminance value of the reference point Pri is greater than a threshold value t2.
- a threshold value t2 is set in advance by experimentation or by another means so that the attention line La is not assessed to be on the same three-dimensional object.
- the three-dimensional object detection unit 33a then adds the attribute b for all of the attention points Pa on the attention line La and determines the evaluation value in the perpendicular equivalent direction to thereby assess whether an edge line is attributable to a three-dimensional object and whether a three-dimensional object is present.
- the threshold value changing unit 37a changes the edge threshold value t described above based on the final edge intensity that is calculated by the edge intensity calculation unit 36. Specifically, the threshold value changing unit 37a determines that the lens is more clouded as the final edge intensity decreases and changes the edge threshold value t in the detection areas A1, A2 to a lower value. Therefore, detecting a three-dimensional object becomes easier even when the lens is clouded, and as a result, detecting an adjacent vehicle V2 becomes easier. On the other hand, the threshold value changing unit 37a determines that the lens is less clouded as the final edge intensity increases and changes the edge threshold value t in the detection areas A1, A2 to a higher value. Accordingly, suppressing noise or the like becomes easier, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- FIG. 26 is a flowchart illustrating the details of the method for detecting an adjacent vehicle according to the second embodiment.
- the operation associated with detection area A1 will be described for the sake of convenience, but the same operation is also executed for the detection area A2.
- Step S301 a predetermined area specified by the view angle a and the attachment position is captured by the camera 10, and the image data of the captured image P captured by the camera 10 is acquired by the computer 30a.
- the viewpoint conversion unit 31 converts the viewpoint of the acquired image data and generates the bird's-eye view image data in Step S302.
- Step S303 the luminance difference calculation unit 38 sets the attention line La on the detection area A1. At this time, the luminance difference calculation unit 38 sets a line corresponding to a line extending in the perpendicular direction in real space as the attention line La.
- Step S304 the luminance difference calculation unit 38 sets the reference line Lr on the detection area A1. The luminance difference calculation unit 38 sets as the reference line Lr a line that corresponds to a line extending in the perpendicular direction in real space and a line that is also separated by a predetermined distance in real space from the attention line La.
- the luminance difference calculation unit 38 sets a plurality of attention points Pa on the attention line La in Step S305. At this time, the luminance difference calculation unit 38 sets a certain number of attention points Pa that will not be problematic for the edge line detection unit 39 during edge detection. The luminance difference calculation unit 38 subsequently sets the reference points Pr so that the attention points Pa and the reference points Pr have the same height in real space in Step S306. The attention points Pa and the reference points Pr thereby substantially line up in the horizontal direction, and the edge line extending in the perpendicular direction in real space is more readily detected.
- the luminance difference calculation unit 38 calculates the luminance difference between the attention points Pa and the reference points Pr at the same height in real space.
- the edge line detection unit 39 then calculates the attribute s of each attention point Pa based on the luminance difference calculated by the luminance difference calculation unit 38 in accordance with formula 1 described above.
- the attribute s of each attention point Pa is calculated using the edge threshold value t for detecting the edges of a three-dimensional object. This edge threshold value t may be changed in the threshold value changing process mentioned below; in the case that the edge threshold value t is changed, the changed edge threshold value will be used in this Step S307.
- Step S308 the edge line detection unit 39 then calculates the continuity c of the attribute s of the attention points Pa in accordance with formula 2.
- Step S309 the edge line detection unit 39 further assesses whether a value obtained by normalizing the sum of the continuity c is greater than a threshold value ⁇ in accordance with formula 3 described above.
- the edge line detection unit 39 detects the attention line La as the edge line in Step S310. The operation then proceeds to Step S311.
- Step S311 determines that the normalized value is not greater than the threshold value ⁇ (S309 : No)
- the edge line detection unit 39 does not detect that the attention line La is an edge line, and the operation proceeds to Step S311.
- Step S311 the computer 30a determines whether the operations of Steps S303 to S310 have been executed for all of the attention lines La that can be set on the detection area A1.
- Step S312 the three-dimensional object detection unit 33a calculates the change in luminance along the edge line for each edge line detected in Step S310.
- the three-dimensional object detection unit 33a calculates the change in luminance of the edge lines in accordance with any of formulas 4, 5, and 6.
- Step S313 the three-dimensional object detection unit 33a excludes, from among the edge lines, the edge lines for which the change in luminance is at a predetermined threshold value tb or greater. In other words, when an edge line having a large change in luminance is not assessed to be a correct edge line, the edge line is not used for detecting a three-dimensional object.
- the predetermined threshold value tb is determined by experimentation or by another means in advance and is set based on the change in luminance that occurs due to the characters on the road surface, roadside vegetation, and the like.
- the three-dimensional object detection unit 33a determines that an edge line having a change in luminance that is less than a predetermined threshold value tb is an edge line of a three-dimensional object and thereby detects the three-dimensional object present in an adjacent lane.
- Step S314 a determination is made by the three-dimensional object assessment unit 33a regarding whether the quantity of edge lines is a predetermined threshold value ⁇ or higher.
- the threshold value ⁇ is set in advance by experimentation or by another means; for example, when a four-wheel vehicle is set as the three-dimensional object to be detected, the threshold value ⁇ is set in advance by experimentation or by another means based on the number of edge lines of a four-wheel vehicle that appeared in the detection area A1.
- the three-dimensional object detection unit 33a determines that a three-dimensional object is present in the detection area A1
- the operation proceeds to Step S315, and an assessment is made that an adjacent vehicle is present.
- the three-dimensional object detection unit 33a determines that a three-dimensional object is not present in the detection area A1
- the operation proceeds to Step S316, and an assessment is made that an adjacent vehicle is not present within the detection area A1.
- FIG. 27 is a threshold value changing process according to the second embodiment.
- the threshold value changing process according to the second embodiment is carried out in parallel with the adjacent vehicle detection process illustrated in FIG. 26 in the same way as in the first embodiment. Additionally, this threshold value changing process is for changing the edge threshold value t for detecting a three-dimensional object so that an adjacent vehicle V2 can be appropriately detected even when the lens is clouded. Accordingly, the edge threshold value t that is changed in this threshold value changing process will be used when detecting the edges of an adjacent vehicle V2 in the adjacent vehicle detection process illustrated in FIG. 26 .
- FIG. 27 is a flowchart illustrating the threshold value changing process according to the second embodiment.
- Step S401 in the same way as Step S201 of the first embodiment, a determination is made regarding whether or not an adjacent vehicle V2 is being detected; when an adjacent vehicle V2 is being detected, the operation waits in Step S401; when an adjacent vehicle V2 is not being detected, the operation proceeds to Step S402, as illustrated in FIG. 27 Then, in Step S402, in the same way as Step S202 in the first embodiment, an assessment is made regarding whether the present is daytime or nighttime; when an assessment has been made that the present is daytime, the operation proceeds to Step S403; when an assessment has been made that the present is nighttime, the operation proceeds to Step S414.
- Steps S403 to S412 the same operation as that in Steps S203 to S212 in the first embodiment is executed. That is, the daytime edge extraction area is first set (Step S403), and the edges of the subject are extracted from the horizon reference area and the pair of left and right road edge reference areas, which are the daytime edge extraction areas (Step S404).
- Step S405 histograms based on the intensity of the extracted edges are generated for the horizon reference area and each of the pair of left and right road edge reference areas (Step S405), and the calculation of the edge intensity deviation S ⁇ (Step S406) and the calculation of the weighting for the edge intensity deviation S ⁇ (Step S407) are conducted for the horizon reference area and the pair of left and right road edge reference areas.
- the intensity of the edges in the horizon reference area and the pair of left and right road edge reference areas is calculated as the target edge intensity, based on the weighting for the edge intensity deviation S ⁇ (Step S408); then, a determination is made regarding whether the target edge intensity in the horizon reference area is a predetermined value or greater (Step S409).
- the target edge intensity in the horizon reference area from among the daytime edge extraction areas is specified as the specific edge intensity (Step S410).
- Step S409 No
- the highest target edge intensity from among the target edge intensities in the horizon reference area and the pair of left and right road edge reference areas, is specified as the specific edge intensity (Step S411).
- the final intensity of the edges in the edge extraction area is then calculated as the final edge intensity based on the specific edge intensity that is specified (Step S412).
- the threshold value changing unit 37a changes the edge threshold value t in the pair of left and right detection areas A1, A2 based on the final edge intensity calculated in Step S412. Specifically, the threshold value changing unit 37a determines that the lens is more clouded as the final edge intensity decreases and changes the edge threshold value t in the detection areas A1, A2 to a lower value. Therefore, detecting a three-dimensional object even when the lens is clouded becomes easier, and as a result, detecting an adjacent vehicle V2 becomes easier. On the other hand, the threshold value changing unit 37a determines that the lens is less clouded as the final edge intensity increases and changes the edge threshold value t in the detection areas A1, A2 to a higher value. Accordingly, suppressing noise or the like becomes easier, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- Step S414 to S421 the same operation as that in Steps S214 to S221 in the first embodiment is executed. That is, the left-side road edge reference area and the right-side road edge reference area, which reference the left and right road edges, are set as the nighttime edge extraction areas (Step S414), and the edges of the subject are extracted from the pair of left and right road edge reference areas, which are set as the nighttime edge extraction areas (Step S415), as illustrated in FIG. 11 .
- Step S416 histograms corresponding to each of the pair of left and right road edge reference areas are generated based on the edges that have been extracted from the pair of left and right road edge reference areas, as illustrated in FIG. 15 (Step S416); the edge intensity deviation S ⁇ is calculated (Step S417) for each of the pair of left and right road edge reference areas; and the weightings for these edge intensity deviations S ⁇ are calculated (Step S418).
- the intensities of the edges in the left-side road edge reference area and the right-side road edge reference area that have been set as the nighttime edge extraction areas are calculated as the target edge intensities, based on the calculated weightings of the edge intensity deviations S ⁇ (Step S419).
- the target edge intensity in the left-side road edge reference area is set as the specific edge intensity for setting the difference threshold th in the left-side detection area A2
- the target edge intensity in the right-side road edge reference area is set as the specific edge intensity for setting the difference threshold th in the right-side detection area A1 (Step S420).
- the final edge intensity for setting the difference threshold th in the right-side detection area A1 and the final edge intensity for setting the difference threshold th in the left-side detection area A2 are calculated, giving consideration to the specific edge intensity that was calculated in the past (Step S421).
- the threshold value changing unit 37a calculates the edge threshold value th in the right-side detection area A1 based on the final edge intensity in the right-side road edge reference area calculated in Step S421 and sets the edge threshold value th in the right-side detection area A1, as illustrated in FIG. 17 .
- the threshold value changing unit 37a calculates the edge threshold value t in the left-side detection area A2 based on the final edge intensity in the left-side road edge reference area calculated in Step S421 and sets the edge threshold value t in the left-side detection area A2, as illustrated in FIG. 17 .
- the edge threshold value t can thereby be set to an appropriate value corresponding to the turbidity of the lens, even when detecting an adjacent vehicle V2 based on the edges; as a result, appropriately detecting a three-dimensional object even when the lens is clouded is possible.
- FIG. 28 is a block view illustrating the details of the computer 30b according to the third embodiment.
- the computer 30b assesses whether or not the lens is clouded and conducts exposure control of the camera 10 according to the turbidity of the lens in order to appropriately detect a three-dimensional object even when the lens of the camera 10 is clouded (when white thin film caused by a water stain or the like has formed on the lens surface).
- the computer 30b is provided with an exposure controller 40 in lieu of the threshold value changing unit 37 of the computer 30 according to the first embodiment.
- Each of the functions of the computer 30b is described below.
- the viewpoint conversion unit 31, the alignment unit 32, the three-dimensional object detection unit 33, the day/night assessment unit 34, and the edge extraction area setting unit 35 are configured in the same way as in the first embodiment, so their descriptions have been omitted.
- the edge intensity calculation unit 36 assesses whether the target edge intensity detected in the horizon reference area within the daytime edge extraction area is a predetermined value or greater; then, the edge intensity calculation unit specifies the target edge intensity detected in the horizon reference area as a specific edge intensity that is used for exposure control when the target edge intensity detected in the horizon reference area is a predetermined value or greater. On the other hand, when the target edge intensity detected in the horizon reference area is less than the predetermined value, the edge intensity calculation unit 36 specifies the highest target edge intensity from among the target edge intensities detected in the horizon reference area and the pair of left and right road edge reference areas as the specific edge intensity that is used for exposure control.
- the edge intensity calculation unit 36 specifies the target edge intensity in the left-side road edge reference area from among the pair of left and right road edge reference areas that have been set as the nighttime edge extraction areas as the specific edge intensity for setting the exposure for the left-side detection area A2; then, the edge intensity calculation unit specifies the target edge intensity in the right-side road edge reference area as the specific edge intensity for setting the exposure for the right-side detection area A1.
- the light environment will differ greatly between the left and right detection areas A1, A2, and the ease with which a three-dimensional object can be detected will also differ greatly due to this type of light environment surrounding the host vehicle V1.
- obtaining an appropriate exposure according to the light environment in each of the pair of left and right detection areas A1, A2 is possible by specifying the target edge intensity in the left-side road edge reference area as the specific edge intensity for setting the exposure for the left-side detection area A2 and by specifying the target edge intensity in the right-side road edge reference area as the specific edge intensity for setting the exposure for the right-side detection area A1; therefore, the detection of a three-dimensional object can be carried out with a high degree of precision.
- the exposure controller 40 conducts exposure control of the camera 10 based on the final edge intensity calculated by the edge intensity calculation unit 36. Specifically, the exposure controller 40 first calculates the exposure control value for controlling the exposure of the camera 10 based on the final edge intensity calculated by the edge intensity calculation unit 36. The exposure controller 40 then sets the exposure of the camera 10 to an appropriate exposure corresponding to the turbidity of the lens by setting the aperture, ISO sensitivity, and the exposure time (or the shutter speed) of the camera 10, based on the calculated exposure control value.
- the exposure control value is a value for controlling the exposure of the camera 10, and the exposure controller 40 decreases the aperture value (opening the aperture to the open side), increases the ISO sensitivity, or lengthens the exposure time as the exposure control value increases. Accordingly, the higher the exposure control value, the more that the exposure amount of the imaging element in relation to the light flux from the subject increases, and clearly capturing the image of the three-dimensional object becomes possible.
- the exposure controller 40 can be configured to control one of the aperture values, the ISO sensitivity, or the exposure time based on the exposure control value; this exposure controller can also be configured to control the aperture value, the ISO sensitivity, and the exposure time simultaneously.
- the exposure controller 40 determines that the lens is more clouded as the final edge intensity decreases and changes the exposure control value to a high value, as illustrated in FIG. 29 . Therefore, detecting a three-dimensional object even when the lens is clouded becomes easier, and as a result, appropriately detecting an adjacent vehicle V2 is possible. On the other hand, the exposure controller 40 determines that the lens is less clouded as the final edge intensity increases and changes the exposure control value to a low value. Accordingly, noise can be effectively suppressed, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- FIG. 29 is a view illustrating one example of the relationship between the exposure control value and the final edge intensity.
- the exposure controller 40 may possibly individually control the exposure of the image areas that correspond to the pair of left and right detection areas A1, A2.
- the exposure controller 40 can individually control the exposures for the image areas that correspond to the pair of left and right detection areas A1, A2 by mutually differentiating the exposure time in the image areas corresponding to the pair of left and right detection areas A1, A2.
- the exposure controller 40 changes the relationship between the exposure control value and the final edge intensity so that the exposure control value is calculated at a relatively low value, even when the final edge intensity is relatively low, as compared to when the surrounding is not pitch-dark, as illustrated in FIG. 17 . Therefore, effectively preventing the occurrence of an erroneous detection of a three-dimensional object when the surrounding is pitch-dark is possible.
- the exposure controller 40 is able to assess that the surrounding is pitch-dark when the luminance of the entire captured image is equal to or less than a predetermined luminance with which a determination can be made that the surrounding is pitch-dark.
- FIG. 30 is a flowchart illustrating the exposure control process according to the third embodiment.
- the exposure control process described below is carried out in parallel with the adjacent vehicle detection process illustrated in FIG. 18 .
- the camera 10 is therefore set with the exposure that has been set by this exposure control process; as a result, the adjacent vehicle detection process illustrated in FIG. 18 is conducted based on the captured image data that has been captured with the exposure that has been set in this exposure control process.
- the intensity of the edges in the daytime edge extraction areas is then calculated as the target edge intensity (Step S508), and the final edge intensity is calculated based on the target edge intensity (Step S512).
- the exposure controller 40 conducts exposure control of the camera 10 based on the final edge intensity that is calculated in Step S512. Specifically, the exposure controller 40 determines that the lens is more clouded as the final edge intensity decreases and calculates the exposure control value at a high value; the exposure controller determines that the lens is less clouded as the final edge intensity increases and calculates the exposure control value at a low value, as illustrated in FIG. 29 . The exposure controller 40 then decreases the aperture value (the opening of the aperture to the open side), increases the ISO sensitivity, or lengthens the exposure time as the calculated exposure control value increases, thereby increasing the exposure amount of the camera 10 (the imaging element) in relation to the light flux from the subject.
- the aperture value the opening of the aperture to the open side
- the camera 10 can clearly capture the three-dimensional object, and as a result, appropriately detecting a three-dimensional object in the adjacent vehicle detection process, as illustrated in FIG. 18 , is possible even when the lens is clouded.
- the exposure controller 40 increases the aperture value (the closing of the aperture to the closed side), decreases the ISO sensitivity, or shortens the exposure time as the calculated exposure control value decreases, thereby decreasing the exposure amount of the camera 10 (the imaging element) in relation to the light flux from the subject. Accordingly, the generation of noise is suppressed, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- the exposure controller 40 conducts exposure control of the camera 10 so that the same exposure can be obtained in the pair of left and right detection areas A1, A2 when an assessment has been made that the present is daytime, as in this Step S513.
- the exposure in the pair of left and right detection areas A1, A2 can be set based on the calculated exposure control value.
- the exposure control value based on edges that best correspond to the turbidity of the lens from among the edges that are extracted from the horizon reference area and the pair of left and right road edge reference areas is possible, and the exposure can be set for both the right-side detection area A1 and the left-side detection area A2 based on the exposure control value; therefore, appropriately detecting a three-dimensional object in the right-side detection area A1 and the left-side detection area A2 is possible.
- Step S502 when an assessment has been made that the present is nighttime in Step S502, the operation proceeds to Step S514.
- Steps S514 to S521 in the same way as in Steps S214 to S221 in the first embodiment, the left-side road edge reference area and the right-side road edge reference area that reference the left and right road edges are set as the nighttime edge extraction areas (Step S514), and the edges of the subject are extracted from the nighttime edge extraction areas (Step S515).
- the intensity of the edges in the nighttime edge extraction areas is then calculated as the target edge intensity (Step S519), and the final edge intensity is calculated based on the target edge intensity (Step S521).
- Step S522 the exposure controller 40 sets the exposures in the right-side detection area A1 from among the pair of left and right detection areas A1, A2; in Step S523, the exposure controller 40 sets the exposure in the left-side detection area A2 from among the pair of left and right detection areas A1, A2. Specifically, the exposure controller 40 determines that the lens is more clouded as the final edge intensity calculated in Step S221 decreases and changes the exposure control value to a high value, as illustrated in FIG. 29 .
- the exposure controller 40 determines that the lens is less clouded as the final edge intensity increases and changes the exposure control value to a low value. Accordingly, the generation of noise is suppressed, and as a result, effectively preventing an erroneous detection of a three-dimensional object is possible.
- the exposure controller 40 calculates the exposure control value in the right-side detection area A1 based on the final edge intensity in the right-side road edge reference area calculated in Step S521 and sets the exposure in the right-side detection area A1, as illustrated in FIG. 29 .
- the exposure controller 40 calculates the exposure control value in the left-side detection area A2 based on the final edge intensity in the left-side road edge reference area calculated in Step S521 and sets the exposure in the left-side detection area A2, as illustrated in FIG. 29 .
- the exposure controller 40 sets the exposure in the left-side detection area A1 and the exposure in the right-side detection area A2separately in this manner when an assessment is being made that the present is nighttime. Accordingly, appropriately detecting a three-dimensional object even when the light environment differs in the right side and the left side of the host vehicle V1 at night is possible.
- the exposure controller 40 changes the relationship between the exposure control value and the final edge intensity so that the exposure control value is calculated at a relatively low value even when the final edge intensity is relatively low, as compared to when the surrounding is not pitch-dark, as illustrated by the broken line in FIG. 29 . Therefore, effectively preventing the occurrence of an erroneous detection of a three-dimensional object when the surrounding is pitch-dark becomes possible, and detecting the edges of the subject due to the lens being erroneously assessed as being clouded is difficult.
- an area from which a predetermined quantity of edges can be expected to be extracted is set as an edge extraction area, and exposure control of the camera 10 is conducted based on the intensity of the edges in the edge extraction area. Specifically, a determination is made that the lens is more clouded as the intensity of the edges (the final edge intensity) decreases in the edge extraction area, and the exposure amount of the camera 10 (the imaging element) in relation to the light flux from the subject increases by increasing the exposure control value, as illustrated in FIG. 29 . Therefore, detecting a three-dimensional object becomes easier, and appropriately detecting a three-dimensional object even when the lens is clouded is possible.
- the lens is more clouded as the intensity of the edges in the edge extraction area increases, and the exposure amount of the camera 10 (the imaging element) in relation to the light flux from the subject decreases by decreasing the exposure control value. Therefore, effectively preventing an erroneous detection of a three-dimensional object caused by noise or the like when the lens is not clouded becomes possible.
- the difference in the exposures between the pair of left and right detection areas A1, A2 when an assessment has been made that the present is daytime becomes equal to or less than the difference in the exposures between the pair of left and right detection areas A1, A2 when an assessment has been made that the present is nighttime.
- the difference in the light environment between the right-side detection area A 1 and the left-side detection area A2 will be determined to be little, so that appropriate exposures based on the final edges can be set for both the right-side detection area A1 and the left-side detection area A2; therefore, the appropriate detection of a three-dimensional object in the right-side detection area A1 and the left-side detection area A2 is possible.
- the determination will be that there are cases in which there is a considerable difference in the light environment between the right-side detection area A1 and the left-side detection area A2 due to the effect of a light source or the like; therefore, appropriately detecting a three-dimensional object according to the surrounding light environment becomes possible by conducting exposure control separately for the pair of left and right detection areas A1, A2, so that an exposure corresponding to the light environment of each of the pair of left and right detection areas A1, A2 can be obtained.
- FIG. 31 is a block view illustrating the details of the computer 30c according to the fourth embodiment.
- the computer 30c according to the fourth embodiment is provided with an exposure controller 40a in lieu of the threshold value changing unit 37 of the computer 30a according to the second embodiment.
- the viewpoint conversion unit 31, the luminance difference calculation unit 38, the edge line detection unit 39, the three-dimensional object detection unit 33a, the day/night assessment unit 34, the edge extraction area setting unit 35, and the edge intensity calculation unit 36 are configured in the same way as in the second embodiment; the exposure controller 40 is configured in the same way as in the third embodiment; therefore, the descriptions thereof have been omitted.
- the adjacent vehicle detection process illustrated in FIG. 26 is executed in the same way as in the second embodiment.
- the exposure control process illustrated in FIG. 30 is executed in the same way as in the third embodiment in conjunction with the adjacent vehicle detection process illustrated in FIG. 26 ; captured image data is captured with the exposure set by this exposure control process; and the adjacent vehicle detection process is conducted based on the captured image data. Accordingly, in the fourth embodiment as well, capturing a three-dimensional object with an appropriate exposure corresponding to the turbidity of the lens is possible; as a result, appropriately detecting a three-dimensional object based on the captured image is possible even when the lens is clouded.
- the adjacent vehicle detection process and the exposure control process according to the fourth embodiment are the same processes as the adjacent vehicle detection process according to the second embodiment and the exposure control process according to the third embodiment; therefore, the description thereof have been omitted.
- the exposure of the camera 10 can thereby be set to an appropriate exposure corresponding to the turbidity of the lens even when detecting an adjacent vehicle V2 based on the edges; as a result, appropriately detecting a three-dimensional object even when the lens is clouded is possible.
- an example configuration was provided in which the difference threshold th or the edge threshold value t are changed based on the intensity of the edges (the final edge intensity) in the daytime edge extraction areas or in the nighttime edge extraction areas; however, no limitation is imposed thereby; for example, there is the possibility of using a configuration in which the values of a threshold value ⁇ and a threshold value ⁇ for detecting a three-dimensional object are changed in lieu of the difference threshold th and the edge threshold value t or in addition to the difference threshold th and the edge threshold value t.
- a threshold value ⁇ and a threshold value t2 for detecting the edge lines are changed or a configuration in which a threshold value tb is changed, based on the intensity of the edges (the final edge intensity) in the daytime edge extraction areas or the nighttime edge extraction areas.
- a configuration in which the pixel value or the luminance value output from each pixel is changed, based on the intensity of the edges (the final edge intensity) in the daytime edge extraction areas or the nighttime edge extraction areas. For example, the detection of a three-dimensional object can be promoted by determining that the lens is more clouded as the final edge intensity decreases and by increasing the pixel value or the luminance value that is output from each pixel.
- an example configuration was provided in which a three-dimensional object is detected as an adjacent vehicle V2 when the travelling speed of the three-dimensional object satisfies a predetermined condition; however, no limitation is imposed thereby; for example, there is also the possibility of using a configuration in which the detection of an adjacent vehicle V2 is suppressed by changing the condition mentioned above based on the intensity of the edges (the final edge intensity) in the daytime edge extraction areas or the nighttime edge extraction areas.
- a three-dimensional object is determined to be an adjacent vehicle V2 when the absolute travelling speed of the three-dimensional object is 10 km/h or more and the relative travelling speed of the three-dimensional object in relation to the host vehicle V1 is +60 km/h or less; however, the detection of an adjacent vehicle V2 can be promoted by determining that the lens is clouded when the final edge intensity is low and, for example, by determining that a three-dimensional object is an adjacent vehicle V2 when the absolute travelling speed of the three-dimensional object is 5 km/h or more and the relative travelling speed of the three-dimensional object in relation to the host vehicle V1 is +65 km/h or less.
- a turbidity index indicating the turbidity of the lens is provided as a parameter for detecting a three-dimensional object; when various controls for detecting a three-dimensional object are conducted based on the turbidity index, this turbidity index is calculated based on the final edge intensity in the daytime edge extraction areas or the nighttime edge extraction areas.
- an example configuration was provided in which the target edge intensity is calculated when an adjacent vehicle V2 is being detected; however, no limitation is imposed thereby; for example, there is also the possibility of using a configuration in which the value of the calculated target edge intensity changes between when an adjacent vehicle V2 is being detected and when an adjacent vehicle V2 is not being detected. Specifically, using a configuration in which the target edge intensity is calculated at a low value when an adjacent vehicle V2 is being detected, as compared to when an adjacent vehicle V2 is not being detected, is possible.
- the camera 10 in the embodiments described above corresponds to the image capturing means of the present invention.
- the viewpoint conversion unit 31 corresponds to the image conversion means of the present invention; and the alignment unit 32, the three-dimensional object detection units 33, 33a, the luminance difference calculation unit 38, and the edge line detection unit 39 correspond to the three-dimensional object detection means of the present invention.
- the edge extraction area setting unit 35 and the edge intensity calculation unit 36 correspond to the first edge intensity calculation means and the second edge intensity calculation means of the present invention;
- the day/night assessment unit 34 corresponds to the day/night assessment means of the present invention; and the threshold value changing units 37, 37a and the exposure controllers 40, 40a correspond to the control means of the present invention.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
- Mechanical Engineering (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
- Closed-Circuit Television Systems (AREA)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012166529 | 2012-07-27 | ||
JP2012166528 | 2012-07-27 | ||
PCT/JP2013/070309 WO2014017625A1 (ja) | 2012-07-27 | 2013-07-26 | 立体物検出装置および立体物検出方法 |
Publications (3)
Publication Number | Publication Date |
---|---|
EP2879386A1 EP2879386A1 (en) | 2015-06-03 |
EP2879386A4 EP2879386A4 (en) | 2015-07-22 |
EP2879386B1 true EP2879386B1 (en) | 2018-01-03 |
Family
ID=49997430
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP13823494.3A Active EP2879386B1 (en) | 2012-07-27 | 2013-07-26 | Three-dimensional object detection device, and three-dimensional object detection method |
Country Status (5)
Country | Link |
---|---|
US (1) | US9591274B2 (ja) |
EP (1) | EP2879386B1 (ja) |
JP (1) | JP5981550B2 (ja) |
CN (1) | CN104509101B (ja) |
WO (1) | WO2014017625A1 (ja) |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103080976B (zh) * | 2010-08-19 | 2015-08-05 | 日产自动车株式会社 | 三维物体检测装置和三维物体检测方法 |
US9349057B2 (en) * | 2011-09-12 | 2016-05-24 | Nissan Motor Co., Ltd. | Three-dimensional object detection device |
US8903127B2 (en) * | 2011-09-16 | 2014-12-02 | Harman International (China) Holdings Co., Ltd. | Egomotion estimation system and method |
JP2015200976A (ja) * | 2014-04-04 | 2015-11-12 | 富士通株式会社 | 移動量推定装置、移動量推定方法、およびプログラム |
JP6130325B2 (ja) * | 2014-04-24 | 2017-05-17 | 本田技研工業株式会社 | 道路環境認識装置 |
WO2015162910A1 (ja) * | 2014-04-24 | 2015-10-29 | パナソニックIpマネジメント株式会社 | 車載用表示装置、車載用表示装置の制御方法、プログラム |
US9785837B2 (en) * | 2014-10-21 | 2017-10-10 | Bae Systems Information And Electronic Systems Integration Inc. | Measuring atmospheric attributes using multispectral images |
JP6657925B2 (ja) * | 2015-06-04 | 2020-03-04 | ソニー株式会社 | 車載カメラ・システム並びに画像処理装置 |
JP7066607B2 (ja) * | 2015-08-03 | 2022-05-13 | トムトム グローバル コンテント ベスローテン フエンノートシャップ | ローカライゼーション基準データを生成及び使用する方法及びシステム |
JP6658054B2 (ja) * | 2016-02-16 | 2020-03-04 | トヨタ車体株式会社 | 車体部品の施工部位判定システム及び施工部位判定方法 |
US9975480B2 (en) | 2016-04-12 | 2018-05-22 | Denso International America, Inc. | Methods and systems for blind spot monitoring with adaptive alert zone |
US9947226B2 (en) | 2016-04-12 | 2018-04-17 | Denso International America, Inc. | Methods and systems for blind spot monitoring with dynamic detection range |
US9994151B2 (en) | 2016-04-12 | 2018-06-12 | Denso International America, Inc. | Methods and systems for blind spot monitoring with adaptive alert zone |
US9931981B2 (en) * | 2016-04-12 | 2018-04-03 | Denso International America, Inc. | Methods and systems for blind spot monitoring with rotatable blind spot sensor |
US11328822B2 (en) * | 2017-02-01 | 2022-05-10 | Conflu3Nce Ltd | Multi-purpose interactive cognitive platform |
JP6832224B2 (ja) * | 2017-04-28 | 2021-02-24 | 株式会社デンソーテン | 付着物検出装置および付着物検出方法 |
US10579067B2 (en) * | 2017-07-20 | 2020-03-03 | Huawei Technologies Co., Ltd. | Method and system for vehicle localization |
US10489677B2 (en) * | 2017-09-07 | 2019-11-26 | Symbol Technologies, Llc | Method and apparatus for shelf edge detection |
JP7401273B2 (ja) * | 2019-11-26 | 2023-12-19 | 日立Astemo株式会社 | 移動体の制御装置及び方法 |
US20230150661A1 (en) * | 2021-11-18 | 2023-05-18 | Aurora Flight Sciences Corporation, a subsidiary of The Boeing Company | Horizon detection to support an aircraft on a mission in an environment |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003044863A (ja) * | 2001-07-30 | 2003-02-14 | Nissan Motor Co Ltd | 仕切線認識装置 |
WO2003093857A2 (en) * | 2002-05-03 | 2003-11-13 | Donnelly Corporation | Object detection system for vehicle |
JP3722487B1 (ja) * | 2004-05-19 | 2005-11-30 | 本田技研工業株式会社 | 車両用走行区分線認識装置 |
JP4130434B2 (ja) * | 2004-11-30 | 2008-08-06 | 本田技研工業株式会社 | 撮像装置の異常検知装置 |
JP4730589B2 (ja) | 2005-04-28 | 2011-07-20 | アイシン精機株式会社 | 車両周辺監視システム |
KR101075615B1 (ko) * | 2006-07-06 | 2011-10-21 | 포항공과대학교 산학협력단 | 주행 차량의 운전자 보조 정보 생성 장치 및 방법 |
JP2008219063A (ja) | 2007-02-28 | 2008-09-18 | Sanyo Electric Co Ltd | 車両周辺監視装置及び方法 |
JP4969359B2 (ja) | 2007-07-31 | 2012-07-04 | ダイハツ工業株式会社 | 移動物認識装置 |
FR2923016B1 (fr) * | 2007-10-31 | 2009-11-20 | Valeo Vision | Procede de detection d'un phenomene perturbateur de visibilite pour un vehicule. |
EP2352013B1 (en) * | 2010-02-01 | 2013-01-23 | Autoliv Development AB | A vision system and method for a motor vehicle |
-
2013
- 2013-07-26 CN CN201380040049.3A patent/CN104509101B/zh active Active
- 2013-07-26 JP JP2014527024A patent/JP5981550B2/ja active Active
- 2013-07-26 US US14/410,760 patent/US9591274B2/en active Active
- 2013-07-26 WO PCT/JP2013/070309 patent/WO2014017625A1/ja active Application Filing
- 2013-07-26 EP EP13823494.3A patent/EP2879386B1/en active Active
Non-Patent Citations (1)
Title |
---|
None * |
Also Published As
Publication number | Publication date |
---|---|
US20150195496A1 (en) | 2015-07-09 |
CN104509101A (zh) | 2015-04-08 |
JPWO2014017625A1 (ja) | 2016-07-11 |
JP5981550B2 (ja) | 2016-08-31 |
US9591274B2 (en) | 2017-03-07 |
CN104509101B (zh) | 2017-12-01 |
EP2879386A4 (en) | 2015-07-22 |
EP2879386A1 (en) | 2015-06-03 |
WO2014017625A1 (ja) | 2014-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2879386B1 (en) | Three-dimensional object detection device, and three-dimensional object detection method | |
RU2636120C2 (ru) | Устройство обнаружения трехмерных объектов | |
EP2879384B1 (en) | Three-dimensional object detection device | |
EP2879382B1 (en) | Three-dimensional object detection device and foreign object detection device | |
EP2819090B1 (en) | Three-dimensional object detection device | |
EP2879110B1 (en) | Three-dimensional object detection device, and three-dimensional object detection method | |
EP2843615B1 (en) | Device for detecting three-dimensional object and method for detecting three-dimensional object | |
EP2821958A1 (en) | Three-dimensional object detection device | |
EP2879385B1 (en) | Three-dimensional object detection device and three-dimensional object detection method | |
EP2821982B1 (en) | Three-dimensional object detection device | |
EP2879115B1 (en) | Three-dimensional object detection device | |
US9589193B2 (en) | Three-dimensional object detection device and three-dimensional object detection method | |
EP2821957B1 (en) | Three-dimensional object detection device | |
EP2821981A1 (en) | Three-dimensional object detection device | |
EP2819115B1 (en) | Three-dimensional object detection device | |
JP5668891B2 (ja) | 立体物検出装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20150223 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RA4 | Supplementary search report drawn up and despatched (corrected) |
Effective date: 20150622 |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: H04N 7/18 20060101AFI20150616BHEP Ipc: H04N 5/232 20060101ALI20150616BHEP Ipc: G06K 9/00 20060101ALI20150616BHEP Ipc: B60R 1/00 20060101ALI20150616BHEP |
|
DAX | Request for extension of the european patent (deleted) | ||
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Ref document number: 602013031758 Country of ref document: DE Free format text: PREVIOUS MAIN CLASS: H04N0007180000 Ipc: G06K0009200000 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: H04N 5/232 20060101ALI20170321BHEP Ipc: G06K 9/46 20060101ALI20170321BHEP Ipc: H04N 7/18 20060101ALI20170321BHEP Ipc: G06K 9/20 20060101AFI20170321BHEP Ipc: G06K 9/00 20060101ALI20170321BHEP Ipc: G06T 7/12 20170101ALI20170321BHEP Ipc: H04N 5/217 20110101ALI20170321BHEP Ipc: H04N 101/00 20060101ALI20170321BHEP Ipc: G06T 7/136 20170101ALI20170321BHEP |
|
INTG | Intention to grant announced |
Effective date: 20170406 |
|
GRAJ | Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted |
Free format text: ORIGINAL CODE: EPIDOSDIGR1 |
|
INTC | Intention to grant announced (deleted) | ||
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20170918 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP Ref country code: AT Ref legal event code: REF Ref document number: 960922 Country of ref document: AT Kind code of ref document: T Effective date: 20180115 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602013031758 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20180103 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 960922 Country of ref document: AT Kind code of ref document: T Effective date: 20180103 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 6 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180403 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180403 Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180404 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180503 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 602013031758 Country of ref document: DE |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
26N | No opposition filed |
Effective date: 20181005 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180726 |
|
REG | Reference to a national code |
Ref country code: BE Ref legal event code: MM Effective date: 20180731 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: MM4A |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180726 Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180731 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180731 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180731 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180726 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20130726 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20180103 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180103 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Ref document number: 602013031758 Country of ref document: DE Free format text: PREVIOUS MAIN CLASS: G06K0009200000 Ipc: G06V0030140000 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R081 Ref document number: 602013031758 Country of ref document: DE Owner name: NISSAN MOTOR CO., LTD., YOKOHAMA-SHI, JP Free format text: FORMER OWNERS: CLARION CO., LTD., SAITAMA, JP; NISSAN MOTOR CO., LTD., YOKOSUKA, JP |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20230620 Year of fee payment: 11 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20230531 Year of fee payment: 11 |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20231116 AND 20231122 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20240620 Year of fee payment: 12 |